Anpei Chen Profile
Anpei Chen

@AnpeiC

Followers
716
Following
194
Media
10
Statuses
51

Group head @Inception3D Lab Assistant Professor @Westlake_Uni https://t.co/ZIIpOtFKvd

Hangzhou
Joined April 2021
Don't wanna be here? Send us removal request.
@weichiuma
Wei-Chiu Ma
12 days
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
@jin_linyi
Linyi Jin
13 days
🌺 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 πŸŒ‹ #Wild3D #ICCV2025
5
5
45
@AnpeiC
Anpei Chen
24 days
π˜½π™šπ™žπ™£π™œ 𝙖𝙣𝙙 π™π™žπ™’π™š Being-in-the-world is the basic state of human existence. by Martin Heidegger 𝙃π™ͺπ™’π™–π™£πŸ―π™ Inferencing via One model, One stage; Training in One day using One GPU. https://t.co/iRWtURvrDf by Yue Chen @faneggchen
fanegg.github.io
Human3R: Everyone Everywhere All at Once
@GerardPonsMoll1
Gerard Pons-Moll
25 days
Real time online 3D reconstruction of 3D scene and humans represented with SMPL. https://t.co/SMsxP4iZhT I don't get tired of looking at these results
0
6
53
@AnpeiC
Anpei Chen
1 month
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.
1
2
14
@AnpeiC
Anpei Chen
1 month
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.
2
0
7
@AnpeiC
Anpei Chen
1 month
#TTT3R: 3D Reconstruction as Test-Time Training We offer a simple state update rule to enhance length generalization for #CUT3R β€” No fine-tuning required! πŸ”—Page: https://t.co/HmEvUwMgLJ 1/4 We rebuilt @taylorswift13’s "22" live at the 2013 Billboard Music Awardsβ€”in 3D
5
39
289
@AnpeiC
Anpei Chen
3 months
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
3 months
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,
2
11
71
@AnpeiC
Anpei Chen
4 months
πŸ’» π—˜π˜…π—½π—Ήπ—Όπ—Ώπ—² π—Όπ˜‚π—Ώ π—₯π—²π˜€π˜‚π—Ήπ˜π˜€ & 𝗖𝗼𝗱𝗲 β€’ Demos & videos: https://t.co/AGLXOYMDjT β€’ Preprint on arXiv: https://t.co/SKLhGO9lZc
0
0
7
@AnpeiC
Anpei Chen
4 months
πŸ“’ 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 πŸ“Ή πŸŽ₯ Project: https://t.co/88XWoJozKn @youzn99 @stam_g @SiyuTang3 Dengxin Dai #SIGGRAPH25 #3DGS
4
25
198
@AnpeiC
Anpei Chen
5 months
πŸ“’ We’re presenting two posters at #CVPR2025 today! πŸ—“οΈ June 13 | πŸ•“ 16:00–18:00 | πŸ“ Exhibit Hall D πŸ”Ή Genfusion β€” Booth 61 πŸ”Ή Feat2GS β€” Booth 93 Come by to chat about generative 3D, geometry, and beyond. See you there! #CVPR25 #3Dvision #AI
0
6
23
@AnpeiC
Anpei Chen
6 months
0
1
3
@AnpeiC
Anpei Chen
6 months
Feature up up up πŸ–ΌοΈβœ¨ We tackle the resolution bottleneck of Vision Foundation Models (like DINOv2 & CLIP) with a coordinate-based cross-attention upsampler. Plug and play β€” stronger, faster than ever! πŸš€ https://t.co/CrKBIiGlrT #VisionModels #DeepLearning #ComputerVision
@HaiwenHuang_
Haiwen Huang
6 months
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 β€” simple design, big gains. Try it out! https://t.co/s09BLF8x1e
1
4
58
@AnpeiC
Anpei Chen
7 months
I love this new function! Never miss a beat again. https://t.co/ELeO8lVzof
0
0
4
@AnpeiC
Anpei Chen
7 months
Main contributions: πŸŽ₯ Reconstruction-driven video diffusion model πŸ” Cyclical fusion of reconstruction and generation πŸ‘€ New benchmark for NVS: Masked View Synthesis
0
0
1
@AnpeiC
Anpei Chen
7 months
Too many artifacts for GS reconstruction? Please checkout GenFusion: Closing the Loop between Reconstruction and Generation via Videos 🌐 Project page: https://t.co/z52j0IIsYU πŸ’» Code: https://t.co/UKHjnibZoE #3D #DiffusionModels #ViewSynthesis #GenFusion #CVPR2025
3
39
197
@AnpeiC
Anpei Chen
7 months
Why train when you can adapt? Easi3R unlocks training-free motion estimation from DUSt3R using attention adaptationβ€”no fine-tuning needed! πŸ’‘
@RoverXingyu
Xingyu Chen
7 months
🦣Easi3R: 4D Reconstruction Without Training! Limited 4D datasets? Take it easy. #Easi3R adapts #DUSt3R for 4D reconstruction by disentangling and repurposing its attention maps β†’ make 4D reconstruction easier than ever! πŸ”—Page: https://t.co/9BngrGu7EL
1
17
99
@faneggchen
Yue Chen
7 months
How much 3D do visual foundation models (VFMs) know? Previous work requires 3D data for probing β†’ expensive to collect! #Feat2GS @CVPR 2025 - our idea is to read out 3D Gaussains from VFMs features, thus probe 3D with novel view synthesis. πŸ”—Page: https://t.co/ArpAbYKn33
4
33
260
@angelaqdai
Angela Dai
1 year
How can we generate high-fidelity, complex 3D scenes? @QTDSMQ's LT3SD decomposes 3D scenes into latent tree representations, with diffusion on the latent trees enabling seamless infinite 3D scene synthesis! w/ @craigleili, @MattNiessner https://t.co/wv9bIhkkYi
3
77
318
@3DVconf
International Conference on 3D Vision
1 year
#3DV2025AMA very first guest, Michael J. Black from MPI-IS & Meshcapade @Michael_J_Black! 🌟 πŸ•’ You have now 24 HOURS to ask him anything β€” drop your questions in the comments below. Let's keep it respectful and engaging!
27
7
79
@AnpeiC
Anpei Chen
1 year
Struggling to secure more GPUs for training large X (reconstruction, Gaussian, etc) models? Check out LaRa, a lightweight 3D vision model designed to efficiently handle large-baseline reconstruction challenges https://t.co/nVSX2qx4ol
apchenstu.github.io
LaRa builds a feed-forward 360Β° bounded radiance field model in two days using 4 GPUs.
1
11
128