AI葵(Aoi) 🇹🇼NeRF技術型Vtuber @kwea123 Twitter profile

Pinned Tweet

AI葵(Aoi) 🇹🇼NeRF技術型Vtuber

@kwea123

1 year

The best flythrough I have so far. Here is Shanghai Exhibition Center #LumaFlythroughs

9

13

98

Last Seen Profiles

@orange_ferry

@RobRobby21671

@romanticyuta

@owlgang2024

@1Taif17

@EKSaito_

@RMajadahondaFS

@Frosty52O

@MrsTaylor345

@clkdursun

@casusev

@nxylas

@IndecentLouisa

@TheGriftShop

@ulucia52118879

@Coco10Cubillas

@cha_li_jin

@hangeoleum_

@benhicks29

@IndecentLouisa

@IncognitoBlue4U

@bokeplokalmalam

@yama_thy

@bokeplokalmalam

@yourcutieari

@stw_pdg

@IndecentLouisa

@srap12701739

@benzachot

@JO_Paris2024

@gjh0428

@hifuling

@ThexnewsX

@bibillones

@murkovski

AI葵(Aoi) 🇹🇼NeRF技術型Vtuber

@kwea123

2 years

Do you believe this NeRF is trained for ONLY 3.5MINS 😱? It already surpasses the quality of the methods I've tried: nerfacc, nerfstudio (nerfacto) and instant-ngp! Details and more astounding results down the thread! 🧵... #NeRF #InstantNeRF #mipnerf360

13

69

478

AI葵(Aoi) 🇹🇼NeRF技術型Vtuber

@kwea123

1 year

@fcr0842361 そもそも100mを10秒で走れないだろ

3

8

219

AI葵(Aoi) 🇹🇼NeRF技術型Vtuber

@kwea123

2 years

Guys I hope you are not angry if I tell you that video was fake 😅 It is created by luma AR where I faked the movement of dropping a phone. The breakdown is 👇 @LumaLabsAI

AI葵(Aoi) 🇹🇼NeRF技術型Vtuber

@kwea123

2 years

My phone dropped from the top of the castle while I was taking a video… 😭😭 It was an iPhone 14 pro omg 我的iPhone 從城堡頂端掉下去了，壽終正寢（還是14 pro），要哭死了😭😭 #howtofixaniphone

10

1

46

9

17

160

AI葵(Aoi) 🇹🇼NeRF技術型Vtuber

@kwea123

1 year

Very excited to announce the integration of new real-time rendering tech that we have been long aspiring. The fast rendering, cool loading animation, unprecedented amount of details (the texts are so clear), all blow me up. As always, the most incredible thing is that our team is

Luma AI

@LumaLabsAI

1 year

3D was either pretty, or fast. Now it’s BOTH! Meet Interactive Scenes built with Gaussian Splatting: 🔥Browser & Phone-Friendly: Hyperefficient and fast rendering everywhere 👌Embed Anywhere: 8-20MB streaming files (even smaller soon!) ✨Ultra High Quality offline NeRF renders &

57

335

2K

4

12

159

AI葵(Aoi) 🇹🇼NeRF技術型Vtuber

@kwea123

2 years

Hi, all! I just released my pytorch version of instant-ngp! The aim is to provide a concise and extendable framework for future research based on the amazing work instant-ngp, which only has a CUDA codebase, therefore less easy to manipulate ... (thread)

GitHub - kwea123/ngp_pl: Instant-ngp in pytorch+cuda trained with pytorch-lightning (high quality...

Instant-ngp in pytorch+cuda trained with pytorch-lightning (high quality with high speed, with only few lines of legible code) - kwea123/ngp_pl

github.com

2

15

120

AI葵(Aoi) 🇹🇼NeRF技術型Vtuber

@kwea123

2 years

Almost finished my improvements on nerf360. Comparison here between full instant-ngp (top row) vs fg instant-ngp+bg mipnerf360 (bottom row) Mine has much sharper background details. I'll benchmark on this dataset vs nerfacc which is another fast method

2

15

108

AI葵(Aoi) 🇹🇼NeRF技術型Vtuber

@kwea123

1 year

The real “Lego”!! At luma AI office 🎉

3

5

109

AI葵(Aoi) 🇹🇼NeRF技術型Vtuber

@kwea123

9 months

@yaku_mio 這麼沒禮貌

1

0

75

AI葵(Aoi) 🇹🇼NeRF技術型Vtuber

@kwea123

2 years

帰りに羽田空港の江戸小路をnerfった @LumaLabsAI #hanedaairport

4

9

70

AI葵(Aoi) 🇹🇼NeRF技術型Vtuber

@kwea123

2 years

result from @LumaLabsAI web, still a lot better from my method, and it automatically detects the foreground object so correctly (it keeps the gundam but removes the box, wow) Don't know how much time it took but I suppose it's pretty fast too

1

8

68

AI葵(Aoi) 🇹🇼NeRF技術型Vtuber

@kwea123

2 years

results from ngp_pl of 8min training! Sorry for the slightly tilted video, I will create an easier gui to manipulate this... #instantNeRF #garden #mipnerf360

2

7

67

AI葵(Aoi) 🇹🇼NeRF技術型Vtuber

@kwea123

2 years

Ref-NeuS: Ambiguity-Reduced Neural Implicit Surface Learning for Multi-View Reconstruction with Reflection The mesh is almost GT, wow

3

12

68

AI葵(Aoi) 🇹🇼NeRF技術型Vtuber

@kwea123

1 year

I can finally post my best flythroughs🥳🥳 #LumaFlythroughs

2

8

62

AI葵(Aoi) 🇹🇼NeRF技術型Vtuber

@kwea123

1 year

BIG release from our generative team❗️ TLDR: we can generate fine 3D assets in ~10s now❣️ Please check the orig post for details. Here I’ll show you some tricks you can do to the 3D assets: 1. 🎱Customize the material. Click on the balls on the right to make it look like

Luma AI

@LumaLabsAI

1 year

Meet Genie, a research preview of an all-new kind of generative 3D foundation model #MadeWithGenie 💬 Create 3D things in seconds on Discord ⚡️ Prototype in various styles 🎨 Customize materials 🆓 Free during research preview Try it now 👇

85

269

2K

2

11

62

AI葵(Aoi) 🇹🇼NeRF技術型Vtuber

@kwea123

2 years

Oriental Pearl in Shanghai NO DRONES at all! Photos taken on the other side of the river bank, where we can admire all the buildings on a very long deck. I took one photo each ~20m so that there is enough baseline. In total only 39 photos but result is as great😃💯 @LumaLabsAI

2

7

62

AI葵(Aoi) 🇹🇼NeRF技術型Vtuber

@kwea123

10 months

If you are excited about this, there was another paper that explored the same idea on the fov: - they have even better metrics - the code is open and has pretrained model However it turned out to not do the job on real-world images 🤷‍♂️ you can try.

GitHub - YvanYin/Metric3D: The repo for "Metric3D: Towards Zero-shot Metric 3D Prediction from A...

The repo for "Metric3D: Towards Zero-shot Metric 3D Prediction from A Single Image" and "Metric3Dv2: A Versatile Monocular Geometric Foundation Model..." - YvanYin/Metric3D

github.com

Alex Carlier

@alexcarliera

10 months

Google just revealed an ABSOLUTE depth estimation model 🤯 As opposed to recent depth models (Marigold, PatchFusion) which aim for maximum details, DMD aims to estimate the ABSOLUTE depth (in meters) within the image More details below ⬇️⬇️

27

269

2K

3

8

59

AI葵(Aoi) 🇹🇼NeRF技術型Vtuber

@kwea123

1 year

I captured some insane NeRF today: look at my render, it's better than any word. It's really surprising to me that we luma can handle so many objects with high details now (we aim to make it even sharper soon). I can imagine so many breathtaking renders with this 😲🙀 (1/2)

2

7

54

AI葵(Aoi) 🇹🇼NeRF技術型Vtuber

@kwea123

4 months

oh no 🫨 #LumaDreamMachine

2

3

53

AI葵(Aoi) 🇹🇼NeRF技術型Vtuber

@kwea123

2 years

More hot results from : Family, PSNR 33.17, FPS 6.16

1

51

AI葵(Aoi) 🇹🇼NeRF技術型Vtuber

@kwea123

2 years

alex told me this library: this is extremely useful to compare videos, before I just open two videos side by side and try to pause them at the same time, which is so idiot 😂

GitHub - pixop/video-compare: Split screen video comparison tool using FFmpeg and SDL2

Split screen video comparison tool using FFmpeg and SDL2 - pixop/video-compare

github.com

2

4

48

AI葵(Aoi) 🇹🇼NeRF技術型Vtuber

@kwea123

2 years

My phone dropped from the top of the castle while I was taking a video… 😭😭 It was an iPhone 14 pro omg 我的iPhone 從城堡頂端掉下去了，壽終正寢（還是14 pro），要哭死了😭😭 #howtofixaniphone

10

1

46

AI葵(Aoi) 🇹🇼NeRF技術型Vtuber

@kwea123

10 months

One amazing year @LumaLabsAI 🥳🥳🥳

2

0

45

AI葵(Aoi) 🇹🇼NeRF技術型Vtuber

@kwea123

2 years

instant-ngp with HDR-NeRF extension We can train images with different exposures, and control the exposure during inference! code to be merged into (after I finish testing on real data) #InstantNeRF #instantNGP #HDRNeRF

2

1

45

AI葵(Aoi) 🇹🇼NeRF技術型Vtuber

@kwea123

2 years

How do MVS researchers think about nerfs? I tried MVSNet and few of its extensions 2 years ago, but now I have the impression that it's totally beaten by nerfs, except being slightly faster. Look at the depth quality, up is CasMVSNet (sota back then) and bottom is nerf.

3

44

AI葵(Aoi) 🇹🇼NeRF技術型Vtuber

@kwea123

2 years

Improved version of #DwightHoward dunking video. Sadly he's injured and has to rest for at least two weeks now... There's another alley-oop highlight I would like to do. #nerf

3

6

44

AI葵(Aoi) 🇹🇼NeRF技術型Vtuber

@kwea123

2 years

Depth map: I'm still improving some details, for now I'm using 2 models for fg and bg, fg is instant-ngp and bg is mipnerf360, with almost 0 modification. The most tricky part is to make them agree with each other on the boundary, and that took me 3 entire days...🤣🥲 continue

3

43

AI葵(Aoi) 🇹🇼NeRF技術型Vtuber

@kwea123

2 years

最近看到很多人使用NovelAI生成圖片，但短暫查詢後就發現他是使用未授權的資料集Danbooru來做訓練的，等於是盜版別人圖片，甚至它還進行營利。行為上來說等於花錢買盗版光碟一樣吧。當然目前法律沒有任何規定，但也跟之前吵的沸沸揚揚的mimic（目前已停止營運）一樣，都是游走在道德邊緣。

3

10

43

AI葵(Aoi) 🇹🇼NeRF技術型Vtuber

@kwea123

2 years

Look at those crisp frames...

1

8

43

AI葵(Aoi) 🇹🇼NeRF技術型Vtuber

@kwea123

2 years

My paper! Chinese explanatory stream:

【AI講壇】介紹我寫的論文！ICRA2022 - Flow Supervised Neural Radiance Fields for...

關於NeRF套用在自動駕駛場景的應用，通過了ICRA2022，所以就在同一天介紹囉！https://events.infovaya.com/presentation?id=80239論文在這裡https://drive.google.com/file/d/1kORAX0DOAs7m771EQ693aH7FeRwU...

www.youtube.com

Neural Fields

@neural_fields

2 years

Flow Supervised Neural Radiance Fields for Static-Dynamic Decomposition (ICRA 2022) Authors: Quei-An Chen, Akihiro Tsukada #neuralfieldsoftheday

1

6

27

2

4

43

AI葵(Aoi) 🇹🇼NeRF技術型Vtuber

@kwea123

1 year

身騎赤兔，手握青龍—關二哥隔壁是一身是膽—趙子龍 @LumaLabsAI #LumaAI

2

9

39

AI葵(Aoi) 🇹🇼NeRF技術型Vtuber

@kwea123

4 months

文字以及圖像生成影片。開發這個真的花了比NeRF還要多好幾倍的時間。不過結果非常棒，實在很佩服我們的每位隊友。目前一支影片只能生成五秒鐘，但相信不久後的威力加強版就能提升更多性能！之後我會分享幾個別人生成的很棒的影片😆 #LumaDreamMachine

Luma AI

@LumaLabsAI

4 months

Introducing Dream Machine - a next generation video model for creating high quality, realistic shots from text instructions and images using AI. It’s available to everyone today! Try for free here #LumaDreamMachine

589

2K

7K

3

6

41

AI葵(Aoi) 🇹🇼NeRF技術型Vtuber

@kwea123

1 year

tl;dr use 3d gaussians to render the scene (similar as points but more info per point), achieves astonishing quality and rendering time, training time is also fast

2

6

40

AI葵(Aoi) 🇹🇼NeRF技術型Vtuber

@kwea123

2 years

PFNの4Dスキャン：水族館ver。サイトによると60台以上のカメラから再構成しているので技術自体はそんなに不思議ではないけど、スキャン対象と見せ方が素敵です。自分も水族館大好きなので、ここ（品川水族館）もよく行ってる。ちなみにLINNE LENSというAI生き物認識アプリが使えるこれも結構おすすめ

Preferred Networks

@PreferredNetJP

2 years

【動画】PFN 4D Scan「しながわ水族館海の宝石箱編」を公開しました。動きのある空間を撮影して空間丸ごとフルCGで再構成。揺らめく水の表現や、魚や珊瑚を好きな角度から自由に眺める映像も制作できます。

1

304

998

2

5

38

AI葵(Aoi) 🇹🇼NeRF技術型Vtuber

@kwea123

2 years

大家好，想詢問有沒有vtuber想參加如下連動計畫主題：ＡＩ生圖—真假大對決我會準備許多人畫的圖與ＡＩ生成的圖，然後讓各位來賓猜哪些是人畫的、哪些是ＡＩ畫的。例題像下面這張圖，請猜出哪邊是ＡＩ畫的？詳細參加模式還在思考中，先詢問是否有人有興趣，請在下方留言，謝謝！🙏 #擴散希望

7

12

39

AI葵(Aoi) 🇹🇼NeRF技術型Vtuber

@kwea123

2 years

So happy to join my new company, their progress has been amazing🎊 加入新公司，他們的成果非常令人矚目，剛進群組就感覺眼花撩亂，期許自己也能做出好的貢獻！安定下來後會再告訴大家是哪裡的😍

8

2

38

AI葵(Aoi) 🇹🇼NeRF技術型Vtuber

@kwea123

1 year

I participated in an unofficial #LumaAI capture contest held by iwaken @iwaken71 group I am very excited to see the expansion of luma, and more people contributing to the community. And of course more great art works! 🥰🥰🥰

0

12

39

AI葵(Aoi) 🇹🇼NeRF技術型Vtuber

@kwea123

1 year

對於以前稍微接觸過optical flow與MVS的我來說，這個unimatch的講解是我最近看過最易懂的了，不由得在螢幕面前拍手👏👏 這個研究效果也非常好，推薦大家去看

GitHub - autonomousvision/unimatch: [TPAMI'23] Unifying Flow, Stereo and Depth Estimation

[TPAMI'23] Unifying Flow, Stereo and Depth Estimation - autonomousvision/unimatch

github.com

1

6

38

AI葵(Aoi) 🇹🇼NeRF技術型Vtuber

@kwea123

2 years

thank you all for 2k stars on my nerf_pl! But now I just recommend to use nerfstudio which has more functionalities and more actively maintained

2

36

AI葵(Aoi) 🇹🇼NeRF技術型Vtuber

@kwea123

1 year

與國父的近距離接觸🫡 （⚠️我並沒有跨越欄杆，這是AI重建的場景） I did not cross the barrier, it’s AI generated scene @LumaLabsAI #LumaAI

1

0

36

AI葵(Aoi) 🇹🇼NeRF技術型Vtuber

@kwea123

1 year

My first food scan 😋 baked chicken leg rice 💯 @LumaLabsAI #LumaAI

2

1

35

AI葵(Aoi) 🇹🇼NeRF技術型Vtuber

@kwea123

1 year

@kk19940324 不是啊黑棋先下，是人類先犯規了

2

0

37

AI葵(Aoi) 🇹🇼NeRF技術型Vtuber

@kwea123

2 years

With the newest AR nerf, we can put our nerfed models into real world and reshoot! Here’s gundam in front of a building. This is too cool😍

Luma AI

@LumaLabsAI

2 years

✨ Announcing Luma AR! Starting today, you can teleport back into your memories like you were there again. Reshoot to create natural camera moves 🎥 in captured worlds, again and again, all from your iPhone! Capture. NeRF. AR. Just like that! #ar #nerf

16

122

507

0

5

37

AI葵(Aoi) 🇹🇼NeRF技術型Vtuber

@kwea123

1 year

陽光下蜻蜓飛過來一片片綠油油的稻田 👇Check this link for interactive scene @LumaLabsAI #LumaAI

1

2

35

AI葵(Aoi) 🇹🇼NeRF技術型Vtuber

@kwea123

2 years

Guess where we are! 😆 @LumaLabsAI #LumaAI

2

36

AI葵(Aoi) 🇹🇼NeRF技術型Vtuber

@kwea123

2 years

Just fixed a dataloader bottleneck... now it runs 1.5x faster than before!

GitHub - kwea123/ngp_pl: Instant-ngp in pytorch+cuda trained with pytorch-lightning (high quality...

Instant-ngp in pytorch+cuda trained with pytorch-lightning (high quality with high speed, with only few lines of legible code) - kwea123/ngp_pl

github.com

0

1

35

AI葵(Aoi) 🇹🇼NeRF技術型Vtuber

@kwea123

2 years

UNREAL plugin is now LIVE! You can now import NeRF(s, actually you can import many and it still runs in realtime) into UE. Try it with your projects! 💯💯💯

Luma AI

@LumaLabsAI

2 years

Introducing the Luma✨Unreal Engine alpha! Fully volumetric Luma NeRFs running realtime on Windows in UE 5 for incredible cinematic shots and experiences, starting today! Try now:

86

521

3K

1

2

34

AI葵(Aoi) 🇹🇼NeRF技術型Vtuber

@kwea123

4 months

素晴らしい使い方していただいてありがとうございました。みんなの反応も見て、思わず涙が出てきそうです。

Koya Matsuo

@mazzo

4 months

妻の高校時代の写真（1978年撮影）と、それが動き出した映像 Luma Dream Machine

35

919

6K

0

7

33

AI葵(Aoi) 🇹🇼NeRF技術型Vtuber

@kwea123

2 years

Just implemented the distortion loss proposed in mipnerf360 in my ngp_pl ! This loss encourages the weight distribution to be concentrated, thus reduce floaters and the number of needed sample points. Thread in the following..

GitHub - kwea123/ngp_pl: Instant-ngp in pytorch+cuda trained with pytorch-lightning (high quality...

Instant-ngp in pytorch+cuda trained with pytorch-lightning (high quality with high speed, with only few lines of legible code) - kwea123/ngp_pl

github.com

4

2

34

AI葵(Aoi) 🇹🇼NeRF技術型Vtuber

@kwea123

2 years

給各位程式員的建議： 1. 學習git 2. 學習remote development (遠端在伺服器上寫code) 遠端+跟別人合作，這些都不可或缺，早點學會幫助很大

4

34

AI葵(Aoi) 🇹🇼NeRF技術型Vtuber

@kwea123

1 year

University road 🎓 @LumaLabsAI #LumaAI

0

3

32

AI葵(Aoi) 🇹🇼NeRF技術型Vtuber

@kwea123

1 year

Amazing result at a glance. The code is written mainly in c++/cuda, my prediction is that to be good at nerf, now c++/cuda is indispensable and is what will differentiate your work with others, in an industrial perspective.

Ziwei Liu

@liuziwei7

1 year

Our F2-NeRF is open sourced at: . Feel free to create your own free-trajectory NeRF within 10min :)

2

79

421

3

4

33

AI葵(Aoi) 🇹🇼NeRF技術型Vtuber

@kwea123

2 years

Anyone noticed this Easter egg? ;) @LumaLabsAI

1

2

33

AI葵(Aoi) 🇹🇼NeRF技術型Vtuber

@kwea123

2 years

To reduce the massive "cloud" in volume rendering, mipnerf360 proposed a distortion loss. Below shows its effect in 3d: With distortion loss, the cloud is highly reduced. The implementation is included in my ngp_pl (instant-ngp in pytorch) #instantNeRF

1

9

33

AI葵(Aoi) 🇹🇼NeRF技術型Vtuber

@kwea123

1 year

A very powerful tool for efficient sampling. If you think nerfstudio is too big to understand, this work is a small and efficient plug-and-use tool for you. The memory requirement is also extremely low, it only uses 3gb to train mipnerf360 which is impressive

Zhenjun Zhao

@zhenjun_zhao

1 year

NerfAcc: Efficient Sampling Accelerates NeRFs Ruilong Li, Hang Gao, Matthew Tancik, @akanazawa tl;dr: a PyTorch Nerf acceleration toolbox->efficient sampling in the volumetric rendering pipeline

2

12

62

0

4

32

AI葵(Aoi) 🇹🇼NeRF技術型Vtuber

@kwea123

2 years

結果我這週是邊在上海玩邊工作下週還有海外員工旅行，太爽了 😆😍 現在擴大招募中，實習生也有招喔！歡迎有志之士與我聯繫。現在招募的工作崗位也增加了，歡迎到官網查詢

8

1

31

AI葵(Aoi) 🇹🇼NeRF技術型Vtuber

@kwea123

1 year

We support original Inria file too! And it’s totally FREE

Luma AI

@LumaLabsAI

1 year

🔥 Luma UE Plugin 0.4 is here — now with splats! 📷 Lightning-fast rendering with #GaussianSplatting . Crop, cull, relight—do it all in UE! Plus, NeRF meets splats and next-level VFX integration. And now supporting UE 5.3! Get it now 👉

16

149

626

0

4

30

AI葵(Aoi) 🇹🇼NeRF技術型Vtuber

@kwea123

1 year

Some other 360 captures I promised: I think I'll be addicted to these. The capture process is simpler (basically it's like capturing with two cameras at the same time), and insta360 comes with a huge selfie stick so I can capture at more different heights (and higher places)💯

1

5

29

AI葵(Aoi) 🇹🇼NeRF技術型Vtuber

@kwea123

2 years

Finally, why two models? First, we can guarantee high quality fg rec. with decent bg rec. too, and you can tell from the gundam details. Another advantage is that we can explicity extract the bg like the following video! (fg too but that's obvious so I omit here) Stay tuned!!

1

31

AI葵(Aoi) 🇹🇼NeRF技術型Vtuber

@kwea123

4 months

So as you know, our ios team is not just sitting and chilling during our dream machine development… more amazing stuff to come!

Luma AI

@LumaLabsAI

4 months

Coming soon to Dream Machine - powerful editability and intuitive controls! Here's a sneak-peak of something exciting we are working towards. #LumaDreamMachine Sign up for early access and to be the first to know when it is ready:

94

324

2K

0

2

30

AI葵(Aoi) 🇹🇼NeRF技術型Vtuber

@kwea123

2 years

gundam in video!! #instantNeRF

1

3

30

AI葵(Aoi) 🇹🇼NeRF技術型Vtuber

@kwea123

2 years

值兩個月薪水的電腦😆

6

0

28

AI葵(Aoi) 🇹🇼NeRF技術型Vtuber

@kwea123

1 year

嗶哩嗶哩 ⚡️⚡️ @LumaLabsAI #lumaai

0

2

28

AI葵(Aoi) 🇹🇼NeRF技術型Vtuber

@kwea123

1 year

Went to a temple today and captured it with insta360. The result is almost perfect, except it being a bit dark. I will try to adjust the brightness next time. But enjoy the free fly! (another one down the thread) @LumaLabsAI #LumaAI

3

2

27

AI葵(Aoi) 🇹🇼NeRF技術型Vtuber

@kwea123

1 year

The greatest work I’ve ever participated in

Luma AI

@LumaLabsAI

1 year

A phone, a house, and some neural networks

37

86

860

1

3

28

AI葵(Aoi) 🇹🇼NeRF技術型Vtuber

@kwea123

1 year

Met a friend today and did a demo showing what I’m working on… nothing special was around us so we went to a convenience store 😆 capture was taken very quickly, and we got the result (video) in just 7-8mins. I’m so proud. I also showed him the AR experience and he’s impressed

0

1

27

AI葵(Aoi) 🇹🇼NeRF技術型Vtuber

@kwea123

2 years

面試幾個人之後的感想：請你們多開金口吧😮😱😲 不管寫得好不好、卡不卡，跟考官解釋你的思路都是很重要滴，即使你寫的是一堆義大利麵，你能跟考官解釋清楚他就是美味的義大利麵。像是你定義a=0，即使就這麼一個簡單的東西，你都可以說明你這個變數是代表什麼、等一下要幹嘛，有聲面試比無聲好💯倍

0

3

27

AI葵(Aoi) 🇹🇼NeRF技術型Vtuber

@kwea123

1 year

用我們新開發的Flythroughs，你可以在手機app裡拍攝影片後，由我們的雲端重建內部空間，然後生成一支帶有無人機空拍效果的影片！自從上次嘗試Airbnb內部拍攝的結果還不錯之後，我們就想挑戰房屋內部的NeRF，也是因為這裡也許有市場（不動產的介紹影片）。總之是一個新的嘗試。下收個人開發感想 😆

Luma AI

@LumaLabsAI

1 year

💫 Today we are incredibly excited to release Flythroughs, an app to show off your space with AI-generated cinematic videos that look like professional drone captures! No need for drones, lidar, expensive real estate cameras, and a crew. Record like you're showing the place to a

108

360

2K

3

5

28

AI葵(Aoi) 🇹🇼NeRF技術型Vtuber

@kwea123

9 months

MANY features are added: ✅ better topo ✅ material estimation ✅ integration in ios/web (also a brand renewal on the site design! 😍) ✅ ... This is our first step towards "multimodal AI": at Luma, we don't exclusively focus on "text-to-3d" or "nerf", we believe what makes 3d

Luma AI

@LumaLabsAI

9 months

🔥 Introducing Genie 1.0, our first step towards building multimodal AI. Genie is a text-to-3d model capable of creating any 3d object you can dream of in under 10 seconds with materials, quad mesh retopology, variable polycount, and in all standard formats! Try it on web and in

106

495

3K

3

2

25

AI葵(Aoi) 🇹🇼NeRF技術型Vtuber

@kwea123

2 years

Last video about basketball nerf reconstruction. Did a little camera work to make it look cooler. Look at how long #DwightHoward 's arm is 🦸! The most difficult part is camera pose reconstruction, after that nerf trains pretty well. Very excited about this technology🏀 #nerf

4

6

27

AI葵(Aoi) 🇹🇼NeRF技術型Vtuber

@kwea123

2 years

Some tricks you can do with luma AR: 1. You can also view featured captures! (Though you can’t reshoot) 2. You can scale (two fingers one up & one down) 3. Move (one finger, move) 4. Rotate (two fingers, rotate) @LumaLabsAI #AR

1

4

27

AI葵(Aoi) 🇹🇼NeRF技術型Vtuber

@kwea123

2 years

重量級選手（功耗方面的）

2

0

27

AI葵(Aoi) 🇹🇼NeRF技術型Vtuber

@kwea123

1 year

好久沒有做除NERF以外的深度學習了。多虧了以前工作經驗，我接觸過各種圖像處理任務：物體偵測、追蹤、深度、光流... 等等。然後又有lightning這種方便的工具使用，現在訓練模型真的很簡單，最煩的反而是找到公開資料集然後下載（下載的時間真的超久的）

1

0

26

AI葵(Aoi) 🇹🇼NeRF技術型Vtuber

@kwea123

2 years

怎麼樣才能吸引別的v的注意呢？

9

0

24

AI葵(Aoi) 🇹🇼NeRF技術型Vtuber

@kwea123

3 years

各位v朋友大家好，目前我們有幾位vtuber想要開圍棋聯棋（或者其他好玩圍棋）的直播，不知道有沒有人有興趣呢？目前參加的有我, @MerakChannel @TCHaruru72 是三缺一的狀態！！預計是下週直播，但時間不是問題，只要你有興趣XD 有興趣的請私訊我們其中一位喔～謝謝大家 #台v #台灣vtuber #擴散希望

3

8

24

AI葵(Aoi) 🇹🇼NeRF技術型Vtuber

@kwea123

2 years

BAD-NeRF (bundle adjusted deblur nerf, mix of deblurnerf and barf, lol) performs better and looks easier to implement for nerf deblurring 😎

0

25

AI葵(Aoi) 🇹🇼NeRF技術型Vtuber

@kwea123

2 years

第一次達到40人觀看! 希望大家今後也多多支持💖

2

0

25

AI葵(Aoi) 🇹🇼NeRF技術型Vtuber

@kwea123

1 year

I went hiking today to take my first insta360 captures to apply with luma! 🥳 Here's one result that I'm really satisfied with: Will share more tomorrow 🥰 (our server seems crowded recently, this one took two hours waiting) @LumaLabsAI #LumaAI

1

25

AI葵(Aoi) 🇹🇼NeRF技術型Vtuber

@kwea123

1 year

偶然看到一個很酷的美術展，裡面有各種特別的模型。我滿喜歡這種隨意散步然後剛好碰見意料之外的驚喜的感覺 @LumaLabsAI #lumaai

0

24

AI葵(Aoi) 🇹🇼NeRF技術型Vtuber

@kwea123

2 years

Finally finished setting up my 4090 CUDA+pytorch install. It was really a pain, I had to try all combinations of pytorchs and cudas until I find a working combination which is torch 1.13.0 + cuda 11.8. Had to compile everything and everything... 🙃

4

2

23

AI葵(Aoi) 🇹🇼NeRF技術型Vtuber

@kwea123

1 year

某地的結婚登記所，前面有很浪漫的電話亭 💑💖 @LumaLabsAI #lumaai

0

2

24

AI葵(Aoi) 🇹🇼NeRF技術型Vtuber

@kwea123

2 years

「沈大成」 green rice ball (a Chinese sweet) shop @LumaLabsAI #LumaAI

1

4

23

AI葵(Aoi) 🇹🇼NeRF技術型Vtuber

@kwea123

2 years

Trained a nerf from the #DwightHoward dunking video I shared yesterday: The result is not perfect but I see a lot of potentials! I would love to see the technique be applied to sports replay like this (still not fast enough for real time) GJ T1 league!

2

0

23

AI葵(Aoi) 🇹🇼NeRF技術型Vtuber

@kwea123

2 years

I learned this recently from my teammates Now I can check with granularity which functions are bottleneck. Before what I did is finding function that "I think" is bottleneck and try to optimize it. It is not the correct way to do apparently. Learn this🥳🥳

0

5

23

AI葵(Aoi) 🇹🇼NeRF技術型Vtuber

@kwea123

1 year

禮拜四晚上10點來講最新程式！順便聊聊在美國公司參觀的趣事🥳

第一次在美國直播（講解Gaussian Splatting的cuda code）[English CC]

直播筆記 https://app.conceptboard.com/board/mink-ntxt-x9a6-xseg-9i7qText digest on github: https://github.com/kwea123/gaussian_splatting_notes到美國來參觀公司，順便再開直播講程式主...

www.youtube.com

2

22

AI葵(Aoi) 🇹🇼NeRF技術型Vtuber

@kwea123

2 years

This is the kitchen at my home! A very traditional one. Reshoot in luma AR 💒 Now I can just summon it, walk in and see wherever I like!

1

2

22

AI葵(Aoi) 🇹🇼NeRF技術型Vtuber

@kwea123

2 years

Another CM using our tech!

Arata Fukoe

@Arata_Fukoe

2 years

NeRFという最新技術を用いてHILUX GR SPORTの広告を制作させていただきました。 @LumaLabsAI #NeRF

13

276

2K

2

1

23

AI葵(Aoi) 🇹🇼NeRF技術型Vtuber

@kwea123

4 months

同事們日夜不休的努力，現在隊列幾乎已經空了，大家如果有新想法要測試的現在都不用等待（而且生成時間只要幾分鐘）然後這一天而已生成影片的數量就大大超出我們的想像🤯

2

1

23

AI葵(Aoi) 🇹🇼NeRF技術型Vtuber

@kwea123

1 year

之前我才做過魔獸的360封蓋火鍋版，當時只有電視台的18個角度來做重建，這次太陽隊專門委託了專業人士 @KodyKurth 使用我們的技術重建各個球員的全身模型（有用到非常多台相機在球場上同時攝影！），然後後製成開場動畫。之後每場太陽主場都能看到這支影片喔！然後KD說他下次不會再被偷球了🥹

Luma AI

@LumaLabsAI

1 year

The @suns in the NeRF dimension. @KodyKurth used @LumaLabsAI to process multicam captures of the entire team mid-action for the official arena intro. By combining NeRF technology with spatial VFX and sound, we were able to create an immersive and unique frozen time moment for NBA

10

92

573

2

3

22

AI葵(Aoi) 🇹🇼NeRF技術型Vtuber

@kwea123

2 years

@AndrewTamalunas @TyrannoSaurav @JeroenFrijters He’s just making fun why so serious

0

23

AI葵(Aoi) 🇹🇼NeRF技術型Vtuber

@kwea123

1 year

夜半の鐘声客船に到る這個景點算是唯一人不多的地方了，其他景點人多到爆，根本看不了什麼東西😩 #LumaFlythroughs

3

2

21

AI葵(Aoi) 🇹🇼NeRF技術型Vtuber

@kwea123

2 years

Thank you all for 1k followers on github! I will keep working on the latest NeRF technology!

3

0

22

AI葵(Aoi) 🇹🇼NeRF技術型Vtuber

@kwea123

2 years

以前我看到有人用numpy自刻神經網路+backprop的時候都覺得是吃飽太閒，明明就有現成的可以用不是嗎？而現在nerf很多部分真的都是要自己寫的(fw+bw)，忽然覺得那些練習還是有那麼一點點小用吧但主要還是要精通微積分，程式的部分真的是小case，微分的公式算不出來根本無法寫程式，let's learn math🥳

3

0

22

AI葵(Aoi) 🇹🇼NeRF技術型Vtuber

@kwea123

2 years

My implementation of MINER is almost done! I can achieve the same quality as the paper and visualize block decompositions! github: #coordinatemlp #deeplearning #imagereconstruction

3

1

22

AI葵(Aoi) 🇹🇼NeRF技術型Vtuber

@kwea123

11 months

Amazing, this is the ultimate capture experience With 1 photo you hallucinate your memory in 3D, if you want it to be genuine, capture more views.

Aleksander Holynski

@holynski_

11 months

Excited to share ReconFusion! 3D reconstruction of real-world scenes from only a few photos, powered by diffusion priors: w/ amazing team @ChrisWu6080 @BenMildenhall @philipphenzler @KeunhongP @RuiqiGao @watson_nn @_pratul_ @dorverbin @jon_barron @poolio

9

59

355

0

1

22

AI葵(Aoi) 🇹🇼NeRF技術型Vtuber

@kwea123

1 year

專業攝影加上高精度AI = 漂亮的模型附加說明，我們目前主軸還是nerf的任意視角生成的影片，mesh只是副產品，我們也知道其精確度（至少在 Texture上）遠不如當前各photogrammetry 產品。這部分也在繼續研究當中，有大進展我們都會在官方推特上發表

YORIMIYA

@jav6868

1 year

ご提供頂��たフィギュアたちを3Dスキャンしてみた～！！めちゃめちゃ非常に満足の行く精度が出ててうれしい #LumaAI #NeRF #ホビージャパン

1

27

90

1

2

21

AI葵(Aoi) 🇹🇼NeRF技術型Vtuber

@kwea123

1 year

About Flythroughs: if you don’t care about mesh, UE plug-in, trajectories,… , this app is for you, we make a cool video from your input for you to share. If you want to be creative about whatever is possible, keep with main luma app which will continue to be free.

0

5

22

AI葵(Aoi) 🇹🇼NeRF技術型Vtuber

@kwea123

2 years

Resuming my ngp_pl implementation. Now I'm trying to add the distortion loss proposed in mipnerf360 in order to reduce "floater" and "background collapse". If it's successful, large scenes and outdoor scenes will gain a lot of improvement!

1

0

22

AI葵(Aoi) 🇹🇼NeRF技術型Vtuber

@kwea123

2 years

I always wonder if there's a way to solve the proposal net artifact, this paper partly solves it but I feel like it's not the right way as too many good parts are gone too. Also I didn't know that the artifact looks seriously bad for captures with limited angles... 🫤

AK

@_akhaliq

2 years

Nerfbusters: Removing Ghostly Artifacts from Casually Captured NeRFs abs: project page: github:

3

82

492

3

22

AI葵(Aoi) 🇹🇼NeRF技術型Vtuber

@kwea123

2 years

The most recent large-scale NVS dataset: RTMV is now supported! Samely, almost every scene trains under 5 minutes with test PSNR > 35 😋 (in the background are the testing PSNRs) #instantNGP

0

21