@_akhaliq Thank you, AK!!
Here are links to our
Project page: motion3-to-4.github.io
Github: github.com/Inception3D/Mo…
English
Anpei Chen
56 posts
Anpei Chen
@AnpeiC
Group head @Inception3D Lab Assistant Professor @Westlake_Uni https://t.co/ZIIpOtFKvd
Hangzhou Katılım Nisan 2021
381 Takip Edilen784 Takipçiler
@AnpeiC I am not sure what is happening here but it looks cool
English
#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
English
Loving the presentation!
Anpei Chen@AnpeiC
#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
English
Anpei Chen retweetledi
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
🌺 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
English
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
Gerard Pons-Moll@GerardPonsMoll1
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
English
#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
English
@nikepig_paj @taylorswift13 Thank you Paj, happy to know you like it;)
English
4/4
🔗Page: rover-xingyu.github.io/TTT3R
📄Paper: arxiv.org/abs/2509.26645
💻Code: github.com/Inception3D/TT…
Big thanks to the amazing team!
@RoverXingyu, @faneggchen, @yuliangxiu, Andreas Geiger, @AnpeiC
English
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.
English
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
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
English
@LvZhaoyang Thank you, Zhaoyang, we will include it in our later version👍
English
That's a great survey and thanks for citing our DGS-LRM work as pioneering work in predicting feedforward deformable 3D Gaussians. We have another parallel work 4DGT (4dgt.github.io) which I am really excited about. Its potential in real world data scaling will be huge. Will appreciate if you can help the team also cover this work. Thanks!
English
📢 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
English
@adarsh_baghel_1 @youzn99 @stam_g @SiyuTang3 Indeed, we explicitly model rolling shutter in the data process and leverage depth-driven warping in the forward pass, but not for other issues so far
English
@AnpeiC @youzn99 @stam_g @SiyuTang3 no but that’s not the only thing, does it solve for motion blur, rolling-shutter “jello,” depth-driven warping, sudden bumps, amplified noise, lost resolution and field-of-view?
English
@jbhuang0604 @youzn99 @stam_g @SiyuTang3 Great catch, we will include and discuss localrf, thank you Jiabin.
English
@AnpeiC @youzn99 @stam_g @SiyuTang3 Great results! Congrats! I would appreciate it if you could consider citing our prior work localrf.github.io as you used our video dataset, and it has the same core idea of local reconstruction and rendering for 3D stabilization.
English