@libing_zeng

Working on world model pretraining for robot learning.

 1X Technologies
libingzeng.github.io/
Joined June 2020
  • Tweets62
  • Following239
  • Followers25
Libing Zeng retweeted
Bernt Bornich
@BerntBornichAug 21
Whole body control + NEO looks amazing
65
79
22
1,168
130,178
Libing Zeng retweeted
el.cine
@EHuanglu26 Apr 2025
AI is taking over advertising. ChatGPT 4o is on FLORA AI canvas now, you can edit image, let anyone wear any outfit, hold any product in video ads and.. use Topaz upscale to 4K step by step tutorial:
61
488
45
4,909
553,307
Libing Zeng retweeted
Jiatao Gu
@thoma_gu10 Mar 2022
In this work, we propose StyleNeRF, a 3D-aware generative model for photo-realistic high-resolution image synthesis with high multi-view consistency, which can be trained on unstructured 2D images. Joint work with @LingjieLiu1 (MPII) Peng Wang (HKU) and Christian Theobalt (MPII)
1
4
23
NeuRay was accepted to CVPR2022!😋 We have updated: Paper: arxiv.org/abs/2107.13421 Project page: liuyuan-pal.github.io/NeuRay… Code: github.com/liuyuan-pal/NeuRa… Welcome any discussions or questions!
2
3
17
Tired of taking 100 calibrated images to get a reasonable 3D reconstruction? Our new #NeurIPS2021 paper recovers shape, texture, and illumination of 3D objects from ~8 images in the wild without precise camera poses! jasonyzhang.com/ners
4
86
10
522
Libing Zeng retweeted
AK
@_akhaliq18 Mar 2022
TensoRF: Tensorial Radiance Fields abs: arxiv.org/abs/2203.09517 project page: apchenstu.github.io/TensoRF/
2
55
6
312
Libing Zeng retweeted
Jon Barron
@jon_barron3 Mar 2022
Very glad I can finally talk about our newly-minted #CVPR2022 paper. We extended mip-NeRF to handle unbounded "360" scenes, and it got us ~photorealistic renderings and beautiful depth maps. Explainer video: youtube.com/watch?v=zBSH-k9G… and paper: arxiv.org/abs/2111.12077
23
248
32
1,633
Libing Zeng retweeted
Jon Barron
@jon_barron26 Feb 2021
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! ibrnet.github.io
2
76
10
440
Libing Zeng retweeted
AK
@_akhaliq1 Mar 2022
State-of-the-Art in the Architecture, Methods and Applications of StyleGAN abs: arxiv.org/abs/2202.14020
1
46
2
242
Libing Zeng retweeted
Rinon Gal@RinonGal12 Oct 2021
The Nicolas Cage version of #StyleGAN3-NADA is coming along quite nicely🙃
29
174
71
937
Libing Zeng retweeted
Li-Yi Wei@liyiwei28 Oct 2021
I thought Facebook would be renamed to "Faceverse" about.facebook.com/meta 😁
1
1
6
Single-image view synthesis usually handles just tiny viewpoint changes. Our new paper goes far beyond the input view by combining differentiable point cloud rendering (for 3D awareness) and vector-quantized autoregressive modeling (for extrapolation)
Chris Rockwell@_crockwell13 Aug 2021
Can we create a 3D experience given only a single image? Our #ICCV2021 work PixelSynth fuses 3D and autoregressive techniques to create consistent content across large angle changes in indoor scenes. Look around! 👇 Demo: crockwell.github.io/pixelsyn… arXiv: arxiv.org/abs/2108.05892
2
13
83
CLIP+NeRF: DietNeRF🥗 is now available! *With only 8 images*, DietNeRF is capable of neural rendering quality novel view from a 3D model. You can check out more details here: 👉𝐆𝐢𝐭𝐡𝐮𝐛 : github.com/codestella/puttin… 👉𝐒𝐭𝐞𝐚𝐦𝐥𝐢𝐭 𝐒𝐩𝐚𝐜𝐞 𝐃𝐞𝐦𝐨 : huggingface.co/spaces/flax-c…
7
60
12
283
Libing Zeng retweeted
AK
@_akhaliq14 Oct 2021
ADOP: Approximate Differentiable One-Pixel Point Rendering abs: arxiv.org/abs/2110.06635
62
964
361
4,875
Libing Zeng retweeted
AK
@_akhaliq11 Oct 2021
stylegan3 is out github: github.com/NVlabs/stylegan3
7
369
41
1,961
📯 ICCV 2021 Oral: "Warp Consistency for Unsupervised Learning of Dense Correspondences", with @MDanelljan, @DrFisherYu and Luc Van Gool. Join us Session 8, 13th 9AM and 15th 4PM (EDT) if you want to know more! paper: arxiv.org/abs/2104.03308 video: youtube.com/watch?v=IsMotj7-…
2
20
91
Deep 3D Mask Volume for View Synthesis of Dynamic Scenes • Create a multi-view video dataset • Stereo video ➡️ 3D mask volume (disoccluded regions) ➡️ blend static/dynamic MPI. cseweb.ucsd.edu//~viscomp/pr…
3
13
Announcing @ICCV_2021 workshop on "Unsupervised 3D Learning in the Wild" with an incredible line-up of speakers on this topic! #ICCV2021 🚩 Website: unsup3d.github.io 📅 Time: 7:00-18:00 EDT / 12:00-23:00 BST, 11 Oct 2021 Calendar: calendar.google.com/calendar… (mark it down!)
2
25
3
159
Libing Zeng retweeted
darthgera123@PulkitRega6 Oct 2021
Mind-blowing work
AK
@_akhaliq6 Oct 2021
StyleNeRF: A Style-based 3D Aware Generator for High-resolution Image Synthesis abs: openreview.net/forum?id=iUuz… a 3D-aware generative model that can synthesize high-resolution images with high multi-view consistency
1
2
3
Libing Zeng retweeted
AK
@_akhaliq1 Oct 2021
TöRF: Time-of-Flight Radiance Fields for Dynamic Scene View Synthesis pdf: arxiv.org/pdf/2109.15271.pdf abs: arxiv.org/abs/2109.15271 project page: imaging.cs.cmu.edu/torf/
3
35
10
173
Load more