Anpei Chen (@AnpeiC)

Anpei Chen reposted

Congrong Xu @CongrongX

May 27

Excited to share our new work R³: 3D Reconstruction via Relative Regression. Only 372M params (~⅓ of recent 1B-class baselines), trained on 6×48G GPUs, but competitive on streaming reconstruction. Runs at 30 FPS. Project: kevinxu02.github.io/r3-site/ Paper: arxiv.org/abs/2605.26519

0:25

10

79

614

73,672

Anpei Chen @AnpeiC

May 28

We suggest going back to relative pose modeling, enabling efficient and robust 3D reconstruction with low memory overhead — in both streaming and offline settings. Project: kevinxu02.github.io/r3-site/ Paper: arxiv.org/abs/2605.26519

1:24

15

102

8,608

Anpei Chen @AnpeiC

Apr 20

GlobalSplat: Stop unprojecting, start decoding. 🛠️ We fuse all input views into a fixed set of Global Scene Tokens to build high-fidelity 3D assets without the pixel-wise redundancy. ✅ Higher quality ✅ Better spatial allocation 🔗 r-itk.github.io/globalsplat/ #3DGS

0:19

3

39

282

19,202

Anpei Chen @AnpeiC

Jan 21

0:54

3

929

Anpei Chen @AnpeiC

Jan 21

#Motion324: 3D Motion Reconstruction for 4D Synthesis We offer a feed-forward framework that synthesizes high-quality 4D assets from just a single monocular video. ✅ Mesh ✅ 3D Motion ✅ Feed-Forward ✅ Motion Retargeting Check out 👇 motion3-to-4.github.io

0:19

8

51

285

24,962

Anpei Chen reposted

Wei-Chiu Ma @weichiuma

20 Oct 2025

If you are interested in 3D/4D/Video models, join us tomorrow (10/20) at the #ICCV #Wild3D workshop (Rm 312)! We have an amazing set of all-star speakers! It will be fun! :) @QianqianWang5 @AnpeiC @Jimantha Andrea Vedaldi @angelaqdai @JunGao33210520 @georgiagkioxari

Linyi Jin @jin_linyi

19 Oct 2025

🌺 Join us in Hawaii for Wild3D! We're hosting our 2nd Workshop on 3D Modeling, Reconstruction & Generation in the Wild! Dive into 3D 4D topics, from real-world reconstruction to video generative models & dynamic scene modeling 🌋 #Wild3D #ICCV2025

5

46

9,642

Anpei Chen @AnpeiC

8 Oct 2025

𝘽𝙚𝙞𝙣𝙜 𝙖𝙣𝙙 𝙏𝙞𝙢𝙚 Being-in-the-world is the basic state of human existence. by Martin Heidegger 𝙃𝙪𝙢𝙖𝙣𝟯𝙍 Inferencing via One model, One stage; Training in One day using One GPU. fanegg.github.io/Human3R/ by Yue Chen @faneggchen

Human3R: Everyone Everywhere All at Once

fanegg.github.io

Gerard Pons-Moll @GerardPonsMoll1

7 Oct 2025

Real time online 3D reconstruction of 3D scene and humans represented with SMPL. fanegg.github.io/Human3R/ I don't get tired of looking at these results

0:10

6

52

6,386

Anpei Chen @AnpeiC

1 Oct 2025

4/4 🔗Page: rover-xingyu.github.io/TTT3R 📄Paper: arxiv.org/abs/2509.26645 💻Code: github.com/Inception3D/TTT3R Big thanks to the amazing team! @RoverXingyu, @faneggchen, @yuliangxiu, Andreas Geiger, @AnpeiC

TTT3R: 3D Reconstruction as Test-Time Training

3D Reconstruction as Test-Time Training

rover-xingyu.github.io

16

1,084

Anpei Chen @AnpeiC

1 Oct 2025

3/4 Instead of updating all states uniformly, we incorporate image attention as per-token learning rates. High-confidence matches get larger updates, while low-quality updates are suppressed.

0:20

1

2

15

1,748

Anpei Chen @AnpeiC

1 Oct 2025

2/4 #VGGT: accurate within short clips, but slow and prone to Out-of-Memory (OOM) #CUT3R: fast with constant memory usage, but forgets. We revisit them from a Test-Time Training (TTT) perspective and propose #TTT3R to get all three: fast, accurate, and OOM-free.

0:05

2

9

1,534

Anpei Chen @AnpeiC

1 Oct 2025

#TTT3R: 3D Reconstruction as Test-Time Training We offer a simple state update rule to enhance length generalization for #CUT3R — No fine-tuning required! 🔗Page: rover-xingyu.github.io/TTT3R 1/4 We rebuilt @taylorswift13’s "22" live at the 2013 Billboard Music Awards—in 3D

1:13

5

41

313

45,618

Anpei Chen @AnpeiC

22 Jul 2025

The fields are moving extremely fast, we tried to summarize them base on 3D representations. Please let us know if we missed anything :)

Zhenjun Zhao @zhenjun_zhao

22 Jul 2025

Advances in Feed-Forward 3D Reconstruction and View Synthesis: A Survey Jiahui Zhang, Yuelei Li, @AnpeiC, Muyu Xu, Kunhao Liu, @jianyuan_wang, @xxlong0, @hx_liang95, @zexiangxu, @haosu_twitr, Christian Theobalt, Christian Rupprecht, Andrea Vedaldi, @hpfister, Shijian Lu, @fnzhan0507 tl;dr: in title arxiv.org/abs/2507.14501

2

11

71

5,524

Anpei Chen @AnpeiC

4 Jul 2025

💻 𝗘𝘅𝗽𝗹𝗼𝗿𝗲 𝗼𝘂𝗿 𝗥𝗲𝘀𝘂𝗹𝘁𝘀 & 𝗖𝗼𝗱𝗲 • Demos & videos: lnkd.in/eDPcx6Wv • Preprint on arXiv: lnkd.in/ex6EG3D5

0:25

7

798

Anpei Chen @AnpeiC

4 Jul 2025

📢 Our new paper GaVS – 3D-Grounded Video Stabilization is out! Key idea: feed-forward Dynamic Gaussian Splatting test-time optimization Robust, consistent, and cropping-free 📹 🎥 Project: sinoyou.github.io/gavs @youzn99 @stam_g @SiyuTang3 Dengxin Dai #SIGGRAPH25 #3DGS

0:40

4

23

193

12,459

Anpei Chen @AnpeiC

13 Jun 2025

📢 We’re presenting two posters at #CVPR2025 today! 🗓️ June 13 | 🕓 16:00–18:00 | 📍 Exhibit Hall D 🔹 Genfusion — Booth 61 🔹 Feat2GS — Booth 93 Come by to chat about generative 3D, geometry, and beyond. See you there! #CVPR25 #3Dvision #AI

6

23

2,048

Anpei Chen @AnpeiC

28 Apr 2025

1

3

530

Anpei Chen @AnpeiC

28 Apr 2025

Feature up up up 🖼️✨ We tackle the resolution bottleneck of Vision Foundation Models (like DINOv2 & CLIP) with a coordinate-based cross-attention upsampler. Plug and play — stronger, faster than ever! 🚀 andrehuang.github.io/loftup-… #VisionModels #DeepLearning #ComputerVision

Haiwen Huang

@HaiwenHuang_

22 Apr 2025

Introducing LoftUp! A stronger (than ever) and lightweight feature upsampler for vision encoders that can boost performance on dense prediction tasks by 20%–100%! Easy to plug into models like DINOv2, CLIP, SigLIP — simple design, big gains. Try it out! github.com/andrehuang/loftup

1

4

58

5,323

Anpei Chen @AnpeiC

15 Apr 2025

I love this new function! Never miss a beat again. scholar-inbox.com/scholar-ma…

4

611

Anpei Chen @AnpeiC

7 Apr 2025

Main contributions: 🎥 Reconstruction-driven video diffusion model 🔁 Cyclical fusion of reconstruction and generation 👀 New benchmark for NVS: Masked View Synthesis

0:03

1

674

Anpei Chen @AnpeiC

7 Apr 2025

Too many artifacts for GS reconstruction? Please checkout GenFusion: Closing the Loop between Reconstruction and Generation via Videos 🌐 Project page: genfusion.sibowu.com/ 💻 Code: github.com/Inception3D/GenFu… #3D #DiffusionModels #ViewSynthesis #GenFusion #CVPR2025

0:10

3

37

196

13,594