Noah Snavely @Jimantha Twitter profile

Last Seen Profiles

@Jack51650061

@s2__x333

@v_kilb

@kloven70

@MichelWhittenb

@cukienaknikmati

@ifebamidele

@Marianitahot202

@Ch91772872Frank

@Edible_Trash666

@kingking2l

@Yankees1969315

@tercanti1k

@YunZiiB

@AtjovB

@ingredientsmeow

@AreejJabir

@Deansy91

@eighthblackbird

@galery_basah10

@Terrell9669

@CandrawatiPuji

@jacobo68708942

@antoniasuber

@bokeplokalmalam

@warab_imochi

@lax_fresh_flect

@sparrow_nemanja

@carle_forla

@whippedhjk

@k435tm

@Mustafa89358219

@hibike_noise

@EclipseEle

@LucasWJCarn

@turbanlisever69

Noah Snavely

@Jimantha

4 years

Hello, view synthesis devotees. I invite you to some new work at @eccvconf . We gather tourist photos of famous landmarks and learn a new neural 3D representation that can synthesize new views with natural, modifyable lighting. We call it "Crowdsampling the Plenoptic Function".

10

124

569

Noah Snavely

@Jimantha

5 years

It turns out that YouTube has tons of videos of people pretending to be statues. This is great for learning about the 3D shape of people! Cool new work from @zl548 at CVPR19 from his Google internship.

2

53

235

Noah Snavely

@Jimantha

4 years

Attention all looking glass lovers: This tweet is a shameless plug for a CVPR 2020 paper that asks a dumb question and finds an interesting answer. Can you tell if an image has been horizontally flipped or not?

10

41

235

Noah Snavely

@Jimantha

3 years

We couldn't find a Fundamental matrix visualizer online, so we made one for our vision course. If you are an F-matrix fan, take a look & tell us if you find any problems. And please send pointers to other demos! (Credits: Alek Curless, Sri Chakra Kumar)

9

38

231

Noah Snavely

@Jimantha

5 years

Dear typesetting fanatics: I wrote a short Latex style guide with some tips & tricks that I find useful for making short and nice-looking papers. If you are working on ECCV papers or the like, maybe it will be useful to you, too.

5

60

213

Noah Snavely

@Jimantha

2 years

For stylization fans, @KaiZhang9546 's work called ARF: Artistic Radiance Fields is on Tuesday's docket at @eccvconf . It achieves nice, view-consistent 2D-to-3D style transfer results by fine-tuning a radiance field so that projections resemble the style of an input source image.

AK

@_akhaliq

2 years

ARF: Artistic Radiance Fields abs: project page: github: create high-quality artistic 3D content by transferring the style of an exemplar image, such as a painting or sketch, to NeRF and its variants

2

133

532

3

28

184

Noah Snavely

@Jimantha

7 months

Thank you to @TheOfficialACM for this really kind honor!

Cornell Tech

@cornell_tech

7 months

In honor of his technical achievements, Associate Professor Noah Snavely was recently named a 2023 @TheOfficialACM Fellow. Congrats, Noah! @Jimantha @Cornell #ACM #Fellowship #CS #Faculty #CornellTech

1

6

31

26

5

171

Noah Snavely

@Jimantha

1 year

Do you have the blues because you are getting broken 3D models from COLMAP or other 3D reconstruction pipelines? Ruojin has a nice new paper and codebase that can help! We invite you to check out our work on doppelganger images here:

Ruojin Cai

@ruojin8

1 year

Check out our #ICCV203 paper called Doppelgangers. We train a classifier to detect distinct but visually similar image pairs ("doppelgangers") and apply it to SfM disambiguation, enabling COLMAP to create correct 3D models in hard cases. Project page:

2

36

191

1

22

132

Noah Snavely

@Jimantha

4 years

Dear city lovers: here's new work at @eccvconf on observing many images of a city over time, and learning to factor lighting effects from scene appearance. This factorization lets us relight new images, even from new cities. Here we learn from NYC and create a full day in Paris.

7

19

131

Noah Snavely

@Jimantha

2 years

To all the CVPR-heads out there -- check out @KaiZhang9546 's work on inverse rendering in this morning's oral session! Relightable 3D meshes from photos, with really beautiful results.

AK

@_akhaliq

2 years

IRON: Inverse Rendering by Optimizing Neural SDFs and Materials from Photometric Images abs: project page:

0

33

148

1

13

129

Noah Snavely

@Jimantha

3 months

This is so cool -- congrats to @zhengqi_li , Richard Tucker, and @holynski_ !

Google AI

@GoogleAI

3 months

Congratulations to @zhengqi_li , Richard Tucker, @Jimantha , and @holynski_ . Their paper “Generative Image Dynamics” received the #CVPR2024 Best Paper Award. Read the paper:

8

29

180

7

4

119

Noah Snavely

@Jimantha

1 year

Really proud of @QianqianWang5 for her best student paper award–winning work she presented at the final session of @ICCVConference . Wonderful job, @QianqianWang5 ! And congrats to authors @ruojin8 , Yen-Yu Chang, @zhengqi_li , @BharathHarihar3 , and @holynski_ .

Aleksander Holynski

@holynski_

1 year

. @QianqianWang5 's 🎉Best Student Paper🎉 is being presented at #ICCV2023 tomorrow (Friday)! ▶️"Tracking Everything Everywhere All At Once"◀️ w/ Yen-Yu Chang, @ruojin8 @zhengqi_li @BharathHarihar3 @Jimantha Friday Afternoon Oral & Poster! Come say hi!

1

21

170

7

0

118

Noah Snavely

@Jimantha

3 years

Fitting a CVPR paper in exactly 8 pages is a real Procrustes-style exercise.

6

2

117

Noah Snavely

@Jimantha

4 years

Greetings from View Synthesis Land! Richard Tucker and I had a fun @cvpr2020 paper (from @GoogleAI ) called "Single-View View Synthesis with Multiplane Images". The code (and Colab) is now available. Have fun out there! web: Colab:

0

25

107

Noah Snavely

@Jimantha

5 years

Got an urge to render the world from Internet photo collections? The source code for @moustafaMeshry 's CVPR2019 best paper finalist is now available: . Have fun out there!

1

28

107

Noah Snavely

@Jimantha

5 years

Learned about Notre Dame Cathedral through computer vision and structure from motion, of all things, many years before I ever got a chance to visit. Very sad day.

2

20

105

Noah Snavely

@Jimantha

1 year

Zhengqi’s new work is a very cool approach to single-image animation—these videos are really nifty! This work turns a still image into a looping video by predicting frequency-space motion. It can also make your image interactive. The demo is really nice!

Zhengqi Li

@zhengqi_li

1 year

Excited to share our work on Generative Image Dynamics! We learn a generative image-space prior for scene dynamics, which can turn a still photo into a seamless looping video or let you interact with objects in the picture. Check out the interactive demo:

19

154

855

4

8

96

Noah Snavely

@Jimantha

2 years

This is so cool! Check out Richard Bowen's work today at #3DV2022 . It considers what possible flow fields could arise if you were to hit a hypothetical "play" button on a still image. @3DVconf

AK

@_akhaliq

3 years

Dimensions of Motion: Learning to Predict a Subspace of Optical Flow from a Single Image abs:

0

14

83

3

10

93

Noah Snavely

@Jimantha

4 years

Hey there—code and data for our Crowdsampling the Plenoptic Function paper from @eccvconf is now available for all you tourism-heads out there. github link:

Noah Snavely

@Jimantha

4 years

Hello, view synthesis devotees. I invite you to some new work at @eccvconf . We gather tourist photos of famous landmarks and learn a new neural 3D representation that can synthesize new views with natural, modifyable lighting. We call it "Crowdsampling the Plenoptic Function".

10

124

569

2

22

92

Noah Snavely

@Jimantha

5 years

Hello to all you light field lovers out there! We have new work with John Flynn and others on high-quality view synthesis from a camera array. We use soft layers to make nice pictures. Presented in Tuesday's afternoon oral session at @cvpr19 .

2

22

91

Noah Snavely

@Jimantha

4 years

I have a real soft spot for epipolar geometry—and so this tweet is a crass advertisement for some work of ours at @eccvconf that I think is nice. The idea is to learn local feature descriptors from pairs of images with known camera poses—no ground truth correspondence required.

6

11

91

Noah Snavely

@Jimantha

4 years

I think it is pretty neat. This is work from Cornell Tech with @zl548 , @XianWenqi , and @AbeDavis . You can find out more at , or watch this wonderful teaser video made by @AbeDavis .

8

20

83

Noah Snavely

@Jimantha

2 months

This is so cool! Check out @boyang_deng 's wonderful work on generating Streetscapes -- tours through imaginary street scenes, conditioned on a desired city layout and a text description. I like this wintry result a lot!

Boyang Deng

@boyang_deng

2 months

Thought about generating realistic 3D urban neighbourhoods from maps, dawn to dusk, rain or shine? Putting heavy snow on the streets of Barcelona? Or making Paris look like NYC? We built a Streetscapes system that does all these. See . (Showreel w/ 🔊 ↓)

3

18

114

0

4

83

Noah Snavely

@Jimantha

4 years

Maybe it's just me, but for me, the award for the computer vision project whose webpage has survived for the longest time without breaking is "3D Photography on your Desk" by Jean-Yves Bouguet and Pietro Perona (1998).

2

6

82

Noah Snavely

@Jimantha

6 years

In need of many examples of camera trajectories from videos? Check out our new RealEstate10K dataset! . This is the kind of data we used in our recent Stereo Magnification work on view synthesis (with Tinghui Zhou).

2

38

80

Noah Snavely

@Jimantha

4 years

These results look amazing!

AK

@_akhaliq

4 years

NeX: Real-time View Synthesis with Neural Basis Expansion pdf: abs:

7

68

301

1

11

79

Noah Snavely

@Jimantha

1 year

I'm really proud of @zhengqi_li , who put his heart into the DynIBaR work that got the Best Paper Honorable Mention nod at CVPR. And I'm really sad that he couldn't be there to experience it due to circumstances beyond his control. Thanks for the nice photo and note, @jon_barron !

0

2

78

Noah Snavely

@Jimantha

4 years

Hi everyone. I'm helping to organize tomorrow's ECCV 4D Vision Workshop. We have a lineup of great papers and speakers—some real vision enthusiasts—including @RaquelUrtasun , Michael Ryoo, @davsca1 , Drago Anguelov, @mapo1 , @xiaolonw , & Tom Funkhouser.

4D-VISION workshop at ECCV'20

The 4D Vision Workshop was held on August, 23, 2020, virtually, in conjunction with the European Conference on Computer Vision (ECCV'20) in Glasgow, Scotland. We thank everyone, including our...

sites.google.com

2

12

66

Noah Snavely

@Jimantha

7 years

Zhengqi Li (Cornell PhD student) presents: MegaDepth! Big (100K+), diverse dataset of RGBD images derived from Internet multi-view stereo. Good for training RGB -> depth, generalizable to other datasets (e.g. KITTI). Web: , arXiv:

1

17

65

Noah Snavely

@Jimantha

4 years

This is work with Zhiqiu Lin, Jin Sun, and @abedavis . You can check it out at or visit the CVPR Q&A on "Visual Chirality" on Thursday. Or watch this nice teaser video from @AbeDavis . Thanks! Now back to your timeline.

2

3

64

Noah Snavely

@Jimantha

2 years

I like this cool space-time view synthesis work from lead author @QianqianWang5 and some other friendly people.

AK

@_akhaliq

2 years

3D Moments from Near-Duplicate Photos abs: project page:

2

30

148

1

6

61

Noah Snavely

@Jimantha

4 years

Shamelessly plugging this talk tomorrow (Wednesday). My hat is off to the 3DGV organizers for putting together a great series of talks on cool 3D vision-style work!

Yasutaka Furukawa

@YasutakaFuruka1

4 years

@3_dgv Seminar in 2 days! @Jimantha Noah Snavely will talk about "The Plenoptic Camera", joined by @_pratul_ Pratul Srinivasan and Rick Szeliski. Please distribute the news to students/members in your groups. Youtube: 3/10 11am Pacific 3/10 19:00 UK

0

11

40

1

3

60

Noah Snavely

@Jimantha

2 years

This is so cool -- congrats, @QianqianWang5 !

Cornell Bowers Computing and Information Science

@CornellCIS

2 years

The Google Ph.D. Fellowship Program has selected @QianqianWang5 as one of its 2022 fellows. “I hope that my technology can enable us to create a rich and realistic virtual world,” - Qianqian Wang, computer science Ph.D. student at @Cornell_tech Read more:

0

27

5

1

57

Noah Snavely

@Jimantha

5 years

Hello to all you fashion-heads out there! We invite you to our new ICCV paper on analyzing clothing in millions of photos around the world. We can discover world events and festivals purely from apparel! With U. Mall, K. Matzen, B. Hariharan & K. Bala.

1

10

54

Noah Snavely

@Jimantha

4 years

For all you inverse rendering fanatics out there, some great work on recovering shape, glossy material, and lighting from multiple photos. This is this work of @KaiZhang9546 , Fujun Luan, @QianqianWang5 , and Kavita Bala from @cs_cornell , @CornellECE , and @cornell_tech .

AK

@_akhaliq

4 years

PhySG: Inverse Rendering with Spherical Gaussians for Physics-based Material Editing and Relighting pdf: abs: project page:

0

8

64

1

7

55

Noah Snavely

@Jimantha

4 years

Someone in NYC today was showing off some very precocious parallel parking skills.

1

4

53

Noah Snavely

@Jimantha

4 years

We invite you to check out this nice work on view synthesis for dynamic scenes! Work from @zl548 during his Adobe internship with @oliverwang81 and @simon_niklaus .

Simon Niklaus

@simon_niklaus

4 years

Really great work we did with @zl548 on practical novel view synthesis in space and time. Take any video and move the camera, or slow down the time, or both! Website: With: @zl548 , @oliverwang81 , @Jimantha

6

44

266

2

53

Noah Snavely

@Jimantha

4 years

Very nice work led by @QianqianWang5 on generalizing NeRF by incorporating principles from classic image-based rendering. Along with other work like pixelNeRF and GRF, I'm excited by these demonstrations of cross-scene generalization. (And I love this example miniature scene!)

Jon Barron

@jon_barron

4 years

Training NeRFs per-scene is so 2020. Inspired by image based rendering, IBRNet does amortized inference for view synthesis by learning how to look at input images at render time. 15% drop in error, 80% fewer FLOPs than NeRF. Great work @QianqianWang5 !

2

82

455

0

6

54

Noah Snavely

@Jimantha

6 years

In case you missed it at ECCV: @zl548 has a new dataset called CGIntrinsics. Ludicrously high-quality CG renderings for learning intrinsic images. You can predict state-of-the-art intrinsic images on real photos just by training on CG data! #ECCV2018

0

23

52

Noah Snavely

@Jimantha

4 years

It feels like CVPR20 ended 9 years ago—but I'm only now checking it out. I recommend the great FATE tutorial. On top of the challenges outlined, I imagine there are hurdles even in spearheading such a tutorial—thank you, @timnitGebru & @cephaloponderer !

FATE/CV

Overview

sites.google.com

0

4

51

Noah Snavely

@Jimantha

4 years

I got the chance to read this paper in detail recently, and it is really cool, especially for all you feature matching–heads out there! I love the idea of computing descriptors on the basis of two images at once. Nice work, @oliviawiles1 , Sebastien Ehrhardt, and Andrew Zisserman!

Dmytro Mishkin 🇺🇦 @ECCV2024

@ducha_aiki

4 years

D2D: Learning to find good correspondences for image matching and manipulation @oliviawiles1 , Sebastien Ehrhardt, Andrew Zisserman, @Oxford_VGG Idea: extract features conditionally on 2nd image. 1/

3

26

75

0

9

51

Noah Snavely

@Jimantha

2 years

This nice work on surface reconstruction from Internet photos is being presented today @siggraph !

Jiaming Sun

@JiamingSuen

2 years

Glad to share our work “Neural 3D Reconstruction in the Wild” in SIGGRAPH 2022! We show that with a clever sampling strategy, neural-based 3D reconstruction can be better and faster than COLMAP. Check out the project page at: .

7

55

319

0

2

49

Noah Snavely

@Jimantha

4 years

Very creative use of data!

AK

@_akhaliq

4 years

Reconstructing 3D Human Pose by Watching Humans in the Mirror pdf: abs: project page:

2

26

114

1

2

43

Noah Snavely

@Jimantha

4 years

I've been thinking about this horrible situation all day, and can't imagine what Timnit is going through.

2

0

43

Noah Snavely

@Jimantha

4 years

Wow -- these results look amazing!

Daniel Duckworth

@duck

4 years

Our paper, “NeRF in the Wild”, is out! NeRF-W is a method for reconstructing 3D scenes from internet photography. We apply it to the kinds of photos you might take on vacation: tourists, poor lighting, filters, and all. (1/n)

75

1K

6K

1

5

43

Noah Snavely

@Jimantha

4 years

I'm really excited about this work!

Angjoo Kanazawa

@akanazawa

4 years

View synthesis is super cool! How can we push it further to generate the world *far* beyond the edges of an image? We present Infinite Nature, a method that combines image synthesis and 3D to generate long videos of natural scenes from a single image.

19

457

2K

2

1

42

Noah Snavely

@Jimantha

3 years

If you are a big fan of solids of revolution like me, you might like this very nice work from Shangzhe on modeling them from single images.

Elliott / Shangzhe Wu

@elliottszwu

3 years

Let's turn photos of ancient "revolutionary" (rotationally symmetric) artefacts into 3D and rotate them, or even change the lighting! Our model learns to de-render a single image of a vase into shape, albedo, material & lighting, from just a single-image collection. #CVPR2021

4

39

256

0

5

39

Noah Snavely

@Jimantha

4 years

Totally agree with Beth: "The violence directed at Asian Americans, especially women, children and elderly, is against the very core values America is built on. This is why I am standing up and speaking up today."

0

2

38

Noah Snavely

@Jimantha

5 years

Very cool dataset of historical stereo image pairs!

Kosta Derpanis at #ECCV2024 Milan 🇮🇹

@CSProfKGD

5 years

Xuan Luo, Yanmeng Kong, Jason Lawrence, Ricardo Martin-Brualla, Steve Seitz, KeystoneDepth: Visualizing History in 3D

0

7

24

1

11

37

Noah Snavely

@Jimantha

3 years

Hi all, please consider nominating yourself to be reviewer for #CVPR2022 . And please pass the word along, especially to those whose voices are not well represented in the vision community. This is one way to help guide the field.

#CVPR2024

@CVPR

3 years

#CVPR2022 is seeking additional reviewers. If interested or you want to nominate someone, please fill out the following reviewer nomination form:

1

43

85

0

11

34

Noah Snavely

@Jimantha

1 year

Really nice work from @zhengqi_li that gets very impressive results on view synthesis for dynamic scenes!

Zhengqi Li

@zhengqi_li

1 year

Check out our CVPR 2023 Award Candidate paper, DynIBaR! DynIBaR takes monocular videos of dynamic scenes and renders novel views in space and time. It addresses limitations of prior dynamic NeRF methods, rendering much higher quality views.

3

92

448

0

1

33

Noah Snavely

@Jimantha

4 years

I love these wonderful interpolations and this very nice project!

Ben Mildenhall

@BenMildenhall

4 years

From our latest project, an homage to the original Photo Tourism visualizations by @Jimantha et al. - interpolating between camera pose, focal length, aspect ratio, and scene appearance from different tourist images. More details at @_pratul_ @jon_barron

4

8

52

0

1

34

Noah Snavely

@Jimantha

5 years

I'm a big logo head! I keep seeing ads for Zenni on the train. I'm intrigued by how the stylized Z and N are exact mirror images here, but not in "real life" - one has horizontal lines, the other vertical. Yet no problem interpreting the logo. Cool Gestalt-style logic at work!

0

1

33

Noah Snavely

@Jimantha

4 years

There are few things I find more terror-inducing than cold calling people -- but I am finding that making US election-related volunteer calls leads to some pretty nice conversations. Some folks just want to chat right now.

0

34

Noah Snavely

@Jimantha

10 months

This was really cool! Thank you for organizing @elliottszwu , @ruoshi_liu , and @Haian_Jin ! It was nice seeing everyone at @cornell_tech .

Ruoshi Liu @ ECCV

@ruoshi_liu

10 months

Organizing the first NYC vision workshop was super fun! Shout out to other organizers @elliottszwu @Haian_Jin and especially @Jimantha for the generous support!

3

8

65

0

2

32

Noah Snavely

@Jimantha

3 years

A bunch of us are hanging out inside a nice #ICCV2021 video chat saloon type interface chatting about Infinite Nature right now!

Angjoo Kanazawa

@akanazawa

4 years

View synthesis is super cool! How can we push it further to generate the world *far* beyond the edges of an image? We present Infinite Nature, a method that combines image synthesis and 3D to generate long videos of natural scenes from a single image.

19

457

2K

0

3

32

Noah Snavely

@Jimantha

3 months

This work led by @Haian_Jin is really nice. It takes text-to-image models and teases out their capability to light objects in a controllable way, much like Zero123 does for camera viewpoint. I'm really surprised that conditioning on environment maps can work this well!

Haian Jin

@Haian_Jin

3 months

Check out our recent work “Neural Gaffer: Relighting Any Object via Diffusion” 📷🌈, an end-to-end 2D relighting diffusion model that accurately relights any object in a single image under various lighting conditions. 🧵1/N: Website:

3

18

79

1

5

32

Noah Snavely

@Jimantha

4 years

Yes, I hope our international students (and H-1B holders) can breathe a little easier now.

Mor Naaman (@[email protected])

@informor

4 years

I'm thinking tonight about our international students, PhD and MS students who over the last few years have faced so much uncertainty about their very presence in this country. This is a great moment for them, and a great moment for US universities and the US economy.

14

205

2K

1

0

31

Noah Snavely

@Jimantha

4 years

Is it just me or are ECCV decisions up already? @eccvconf

6

2

30

Noah Snavely

@Jimantha

2 years

This really fun work — Infinite Nature synthesis trained on still photos — with @zhengqi_li , @QianqianWang5 , and @akanazawa will be live at #ECCV2022 on Wednesday! Thanks, and have a great day.

Angjoo Kanazawa

@akanazawa

2 years

A new follow up to infinite nature is out! This time we show how an infinite nature model can be trained on *single image* collections, without any multi-view or video supervision at training time! We call it infinite nature 𝘻𝘦𝘳𝘰 since it requires no video 🙂 #ECCV2022 oral

3

17

193

0

30

Noah Snavely

@Jimantha

2 months

I'm a big fan of work on visual discovery, and this work on using diffusion models for data mining is really cool!

Shiry Ginosar

@shiryginosar

2 months

Image synthesis models can be used for visual data mining! See our new #ECCV2024 paper: "Diffusion Models as Data Mining Tools." Project page: Paper: 1/9

4

21

89

0

1

31

Noah Snavely

@Jimantha

3 years

Happy Lunar New Year, and to all you astronomy fanatics a question -- If you and your family lived for generations in a village on the far side of the Moon, would you realize that the Earth existed?

3

0

29

Noah Snavely

@Jimantha

4 years

These depth maps look amazing! Nice work, @XuanLuo14 and co-authors!

Jia-Bin Huang

@jbhuang0604

4 years

Check out our #SIGGRAPH2020 paper on Consistent Video Depth Estimation. Our geometrically consistent depth enables cool video effects to a whole new level! Video: Paper: Project page:

10

212

887

1

2

29

Noah Snavely

@Jimantha

4 years

We call it "Learning to Factorize and Relight a City". This is the nice work of first author @ndrewLiu at @googleai , and @shiryginosar , @TinghuiZhou , and Alyosha Efros. See more nice videos at !

2

5

28

Noah Snavely

@Jimantha

3 years

Reminder about this CVPR registration support program -- please apply by April 15, 2022 if you'd like to be considered for a registration fee waiver! I hope that this effort can help increase inclusivity of CVPR. Application is here:

CVPR'22 Registration Fee Waiver Request

CVPR'22 is committed to supporting students from communities that do not traditionally attend CVPR through waived registration fees, in order to foster a more inclusive, diverse and equitable...

docs.google.com

#CVPR2024

@CVPR

3 years

#CVPR2022 is committed to supporting students from communities that do not traditionally attend CVPR through waived registration fees, to foster a more inclusive, diverse and equitable conference. 1/2

3

34

126

1

10

29

Noah Snavely

@Jimantha

1 year

I think I'm not mistaken that ICCV camera ready papers this year can be 9 pages+references (not 8)? If that is right, that is a first, and a very welcome, cool, and nice change!

3

1

28

Noah Snavely

@Jimantha

2 years

CVPR Academy is in progress! For all you first-time CVPR fanatics. In Room 202, or accessible though the virtual platform. All the best to you all.

#CVPR2024

@CVPR

2 years

#CVPR2022 Pre-Conference Workshop for First-Time Attendees: On Monday 6/20 AM, Room 202

0

2

17

0

7

28

Noah Snavely

@Jimantha

3 years

For all you photography fanatics out there, a nice blog post about the photo with the longest known sightline captured to date -- 443km, from the Pyrenees to the French Alps.

443 KM | Finestrelles, Pyrenees – Pic Gaspard, Alps

Current Guinness World Record Longest Line of Sight A thin line of Mountains rises over the Horizon: The Alps, with Barre des Écrins (4.102 m) in the middle left of the image. Distance443 Kilometer…

beyondrange.wordpress.com

1

3

28

Noah Snavely

@Jimantha

4 years

Hi there. Code for our @eccvconf work from @cornelltech on learning where people could appear in an image is now online. Our (cool) method learns to predict potential people purely from observing data like Waymo's Open Dataset. Code below—have a good day!

Hadar Averbuch-Elor

@ElorHadar

4 years

Where could people walk? Excited to share our @eccvconf paper on learning contextual walkability: "Hidden Footprints: Learning Contextual Walkability from 3D Human Trails" Arxiv: Website: With: Jin Sun, @QianqianWang5 , @Jimantha

1

13

41

0

5

28

Noah Snavely

@Jimantha

4 years

The upshot is that images seem to be full of low- and high-level chirality cues, and deep networks are pretty good at guessing when an image has been flipped. You might care if you're into data augmentation, image forensics, or self-supervision (or if you are a huge mirror-head).

1

6

27

Noah Snavely

@Jimantha

3 years

For Lunar New Year/Spring Festival, another Moon-based note to all you Moon lunatics out there. One of my favorite gifs on Wikipedia is this one illustrating the apparent wobble of the Moon over the course of a month, called libration.

3

1

27

Noah Snavely

@Jimantha

2 years

Tomorrow is Election Tuesday in the US. I have tons of extra candy. If you see me and show me a "I Voted" sticker, I will try to give you some candy! I have Skittles and Baby Ruths.

1

0

27

Noah Snavely

@Jimantha

3 years

I am sorry for buzz marketing, but if you are looking for a TV show for a 3-5 year old, I recommend a math-themed PBS program called Peg + Cat. Our 4 year old loves it (and the songs are catchy).

2

0

27

Noah Snavely

@Jimantha

3 years

This workshop was so cool! My live talk had some technical difficulties, so if you want to see a clean version of a talk on how to tell if you are in a mirror universe (and a bunch of other great talks on less obscure topics), please check this out!

David Lindell

@DaveLindell

3 years

If you missed the Computational Cameras and Displays Workshop at #CVPR2021 , you can still watch the recorded talks at

1

11

50

5

7

27

Noah Snavely

@Jimantha

3 years

This looks like a wonderful program for computer graphics PhD students and postdocs! Application deadline on April 4, 2022 at

WiGRAPH

@wigraphorg

3 years

Announcing WiGRAPH's Rising Stars in Computer Graphics! Ph.D. students and postdocs of underrepresented genders: apply for a two-year program of mentorship and workshops co-located with SIGGRAPH 2022&2023. Travel support provided. #WiGRAPHRisingStars [1/6]

3

79

195

0

6

26

Noah Snavely

@Jimantha

4 years

I've personally benefited a ton from @timnitGebru and her work. Her earlier work on estimating demographics at scale from Street View has been a big inspiration to me. Her more recent work in ethics is truly foundational, and has helped me think about the world differently.

1

2

25

Noah Snavely

@Jimantha

2 years

If you're a big lover of video decomposition, check out @vickie_ye_ 's nice paper on Deformable Sprites in the CVPR afternoon oral session. We are huge fans of layered video representations!

1

3

24

Noah Snavely

@Jimantha

7 years

Oops.

0

6

24

Noah Snavely

@Jimantha

9 months

This work looks really interesting!

Jerome Revaud

@JeromeRevaud

10 months

We believe we did a breakthrough in Geometric 3D Vision: meet DUSt3R, an all-in-one 3D Reconstruction method

13

55

262

1

3

24

Noah Snavely

@Jimantha

4 years

A deep network takes two images, learns to search for 2D matches between them, and then a loss function decides how much it likes the matches based on how much they deviate from the epipolar constraints derived from the camera poses, as in the visualization below.

3

1

22

Noah Snavely

@Jimantha

4 years

@CSProfKGD Thanks, Kosta! Yes, there was an appearance from a 4-year-old who wasn't happy that I wasn't in play mode. (I moved to a different room, but forgot my trackball, so she started controlling my computer remotely.) I'm glad people seemed to be understanding of the heightened chaos.

4

0

21

Noah Snavely

@Jimantha

3 years

That page also has a stunning photo of the Earth that looks like CGI but is actually a photo from the Lunar Reconnaissance Orbiter. This photo is new to me but is really amazing!

1

3

20

Noah Snavely

@Jimantha

3 years

@taiyasaki @ICCV_2021 Reviewers rock! Thank you so much for your hard work. Some didn't chime into discussions, but I think because CVPR and life was happening. Also, I initiated discussions late... between CVPR and sick kids/self, I was a bad AC☹️. But many reviewers chimed in anyway. Thank you!

1

0

20

Noah Snavely

@Jimantha

4 years

Thanks, Ben! And I should note that the original idea for multiplane images came from John Flynn, working with Graham Fyffe and @debfx . That idea was also presaged in John's prior DeepStereo view synthesis method, as well as Soft3D from Penner and Zhang.

Ben Mildenhall

@BenMildenhall

4 years

Great overview from @fdellaert ! I'd also like to highlight @TinghuiZhou and @Jimantha et al. for bringing volume rendering into deep learning for view synthesis with their paper Stereo Magnification in 2018.

2

28

1

20

Noah Snavely

@Jimantha

3 years

Hi all, ICCV21 isn't even over yet, but #CVPR2022 will be here before we know it, and deadlines for proposing workshops & tutorials are coming up soon. It would be great if the organizers had a diverse set of proposals on a range of topics, including societal impacts of CV.

1

3

20

Noah Snavely

@Jimantha

10 months

This idea is really cool!

Dor Verbin

@dorverbin

10 months

Introducing Eclipse, a method for recovering lighting and materials even from diffuse objects! The key idea is that standard "NeRF-like" data has all we need: a photographer moving around a scene to capture it causes "accidental" lighting variations. (1/3)

5

37

353

0

1

20

Noah Snavely

@Jimantha

2 years

Congrats, @ruojin8 ! This is so cool!

Cornell Tech

@cornell_tech

2 years

Congratulations to CS PhD student Ruojin Cai for being selected as a 2022 Snap Research Fellow! 🎉 Learn more: #CS #PhD #Fellowship #SnapResearch #OnlyAtCornellTech #EngineeredToMatter @Cornell

1

2

11

1

20

Noah Snavely

@Jimantha

7 years

And for all y'all intrinsic image fanatics out there -- Zhengqi also has a cool new paper on learning intrinsic images supervised with time-lapse data: "Learning Intrinsic Image Decomposition by Watching the World". Web: , arXiv:

0

6

19

Noah Snavely

@Jimantha

3 years

A reminder that @CVPR 2022 workshop proposals are due tomorrow, October 19, at 11:59pm Pacific. Thank you! More info here:

0

8

19

Noah Snavely

@Jimantha

3 years

Hope you are all doing well out there. ECCV22 workshop proposals are due tomorrow! it would be wonderful to see a diverse range of workshops at the conference.

European Conference on Computer Vision #ECCV2024

@eccvconf

3 years

#ECCV2022 Call for Workshop Proposals

1

10

46

1

4

18

Noah Snavely

@Jimantha

2 years

Hey everybody -- there is still time to apply to the CVPR 2022 travel grant program. More details in the form:

CVPR 2022 Travel Support Application

CVPR'22 is committed to supporting students from communities that do not traditionally attend CVPR through travel supports. Allocation is based on a combination of need, contribution to the meeting,...

docs.google.com

#CVPR2024

@CVPR

2 years

#CVPR2022 is now accepting applications for travel grants. Decisions will be made on a rolling basis, so please apply soon, and no later than 5/13 at 11:59 CST. Links: (student) (advisor) Source:

0

12

44

1

9

19

Noah Snavely

@Jimantha

4 years

She is a guiding light in computer vision and learning, and she deserves our support.

0

19

Noah Snavely

@Jimantha

4 months

It was a pleasure to attend this wonderful defense! Are you saying that is a hat in the third photo?

Paul-Edouard Sarlin

@pesarlin

4 months

I defended my PhD thesis last week 🥳 Thank you to everyone that made this possible, including my advisor @mapo1 , examiners @Jimantha @quantombone and Daniel Cremers, and the amazing @cvg_ethz . As per the tradition, I received a nice commemorative hat 🎓 Now time for vacations 😎

31

7

355

1

0

18

Noah Snavely

@Jimantha

4 years

For y'all @eccvconf attendees, @zl548 , @XianWenqi , and I are hanging out at the Zoom poster right now.

Noah Snavely

@Jimantha

4 years

Hello, view synthesis devotees. I invite you to some new work at @eccvconf . We gather tourist photos of famous landmarks and learn a new neural 3D representation that can synthesize new views with natural, modifyable lighting. We call it "Crowdsampling the Plenoptic Function".

10

124

569

0

4

18

Noah Snavely

@Jimantha

4 years

For all you ECCV rebuttal writers out there... seems like reviewers can see your rebuttals in OpenReview even before the end of the rebuttal period, which may be surprising behavior to CMT-heads like me.

Daniyar Turmukhambetov

@dantkz

4 years

@CSProfKGD As a reviewer I saw initial rebuttal from authors, and then edited version. So, you can edit, but whatever you have entered is already visible to the reviewers.

1

0

2

18

Noah Snavely

@Jimantha

6 years

Layers! We love layers. On that note, a shameless plug for Shubham Tulsiani's work on *layered scene inference* -- predicting geometry in the form of *layered* depth maps from single images. #ECCV2018 #layers

0

3

18

Noah Snavely

@Jimantha

3 years

@ak92501 I like this. I always wanted something like this to get ground truth data for predicting sun direction from images.

0

16

Noah Snavely

@Jimantha

4 years

I heard some states are rightfully changing up their flag design, so it seemed like a good time to remind folks that my home state of Arizona has the best flag, and Wisconsin has the worst one.

2

0

16

Noah Snavely

@Jimantha

4 years

... low-level artifacts due to JPEG compression and Bayer demosaicing, and high-level elements like shirt collars, musical instruments, and even eye gaze and hair part (?)

3

2

15