PhD Student @Westlake_Uni. Playable world builder. Muggle dreaming of the Wizarding World
Joined December 2022
- Tweets88
- Following331
- Followers380
- Likes280
Pinned Tweet
#Human3R: Everyone Everywhere All at Once
Just input a RGB video, we online reconstruct 4D humans and scene in 𝗢𝗻𝗲 model and 𝗢𝗻𝗲 stage.
Training this versatile model is easier than you think – it just takes 𝗢𝗻𝗲 day using 𝗢𝗻𝗲 GPU!
🔗Page: fanegg.github.io/Human3R/
Yue Chen retweeted
1/5 Excited to share an early exploration.
Coding agents like Codex can already tackle much of real-to-sim—even for robot manipulation. Does that mean 3D vision is solved?
Not quite. 3D still matters.
yubel426.github.io/Plumb/
Yue Chen retweeted
DirtyMoCap recovers 3D human motion from noisy markers. No marker labels or predefined layout.
HKMALA-Motion: 134 Kung Fu sequences, ~3 hours, 22 styles.
#SIGGRAPHAsia2026 🧵
Project: wanglongzju.github.io/DirtyM…
Paper: arxiv.org/abs/2609.19927
Code: github.com/WangLongZJU/Dirty…
Yue Chen retweeted
GaussiAnimate compresses a 4D capture into a rigged 3D asset while keeping its secondary dynamics.
No physics simulation or learned deformable model.
Page: net-maker.github.io/gaussian…
#SIGGRAPHAsia2026 🧵
Yue Chen retweeted
Hiring! Postdoc / Research Leader on human–world interaction, interactive world models and /or human motion & appearance (faces + full body).
virtualhumans.mpi-inf.mpg.de…
Amazing Tübingen ecosystem: @uni_tue @MPI_IS @ELLISforEurope
Feel free to forward to interested people!
Yue Chen retweeted
Check out @aymenmmir ECCV'26 work!
Full 3D GS avatar from a single video. Key idea is to leverage video diffusion to recover the missing parts and feedback to a 3D model which is controllable and cheap to render.
1/4 📢 AHOY! accepted at #ECCV2026! 🎉
From a single in-the-wild YouTube video, often heavily occluded, AHOY builds a complete, animatable 3D human avatar.
Each clip below runs input → 360° avatar → animation. 🧵👇
🔗 miraymen.github.io/ahoy/
Yue Chen retweeted
We present GUSH3R, a feed-forward approach for dynamic human-scene 3DGS reconstruction.
Our model generates per-pixel scene gaussians and per-vertex dynamic human gaussians by dual decoders built on top of Human3R⚡️
Project page (with arXiv and code):
abkeito.github.io/gush3r-pag…
Yue Chen retweeted
Does 3D reconstruction have to be complex?
We answer this question with PointDiT (#ICML2026): a minimalist pixel-space Diffusion Transformer without bells and whistles.
We show that a plain ViT can estimate dense 3D point maps by operating directly on raw patches. No hybrid ViT+Conv architectures, no lossy VAEs, no complicated training losses. (1/5) 🧵👇
Yue Chen retweeted
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
How do I prevent penetration in Human3R?
- I don't. I just take GRAFT home.
Can we reason how human interact with 3D scene?
Given the implausible human in the scene, GRAFT reasons the spatial relationship and recurrently refine the interaction.
With better performance than explicit optimization, GRAFT is also 50x faster 🚀
pradyumnaym.github.io/graft
Yue Chen retweeted
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
Yue Chen retweeted
🚀 Excited to release the code and models of ReSplat: Learning Recurrent Gaussian Splatting!
🌐 Project page: haofeixu.github.io/resplat/
💻 Code & models: github.com/cvg/resplat
Yue Chen retweeted
#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
Yue Chen retweeted
🧟♂️ Introducing FrankenMotion: Part-level motion generation with unified Spatial-Temporal Control!
From fine-grained bodypart descriptions to high-level action goals, we enable you to compose distinct elements into coherent motions.
🔗 Project Page: coral79.github.io/frankenmot…
Yue Chen retweeted
Introducing CARI4D: category agnostic 4D reconstruction of human object interaction. We reconstruct consistent 4D human-object from just an RGB video.
Website: nvlabs.github.io/CARI4D
Paper: arxiv.org/abs/2512.11988
Code: github.com/NVlabs/CARI4D
3:15 p.m — 5:15 p.m
Exhibit Hall I #390
Come and take it Easi3R
🦣Easi3R: 4D Reconstruction Without Training!
Limited 4D datasets? Take it easy.
#Easi3R adapts #DUSt3R for 4D reconstruction by disentangling and repurposing its attention maps → make 4D reconstruction easier than ever!
🔗Page: easi3r.github.io
Yue Chen retweeted
Given a complex real world task, how can an intelligent angent achieve the goal? From a human perspective, it needs to reason when to do what, and how?
Tomorrow I will give a talk about human motion and interaction synthesis with control..
Hope to see many of you there!
🚀 We’ll be hosting a Tutorial on "3D Human Motion Generation and Simulation" at ICCV 2026 in Honolulu, Hawaii! 🌺
📅 Date: October 19, 2026
⏰ Time: 9:00–16:00 (HST)
🔗 More details & resources: 3dmogen.github.io
#AIGC #Simulation #robotics #ComputerVision #ICCV2025
Yue Chen retweeted
UP stands for "Unconstrained Photos." UP2You can transform one, a few, or dozens of "dirty" human photos—regardless of pose, clothing dynamics, occlusion, or cropping—into "clean" orthogonal views that are friendly to MVS reconstruction, and it does so faster than PuzzleAvatar (1.5 minutes vs. 4 hours)
#UP2You: Fast Reconstruction of Yourself from Unconstrained Photo Collections
Just input unconstrained photo collections with dynamic camera poses, body movements, and non-rigid clothing, UP2You reconstructs 3D textured human mesh in 1.5 minutes.
🔗Page: zcai0612.github.io/UP2You/
Yue Chen retweeted
#PhySIC! 🚀
Ever wanted to turn a single photo into a full 3D world where people interact realistically with surrounding? PhySIC does just that, reconstructing both humans and scenes with physically plausible contact.
🔗 Project Page: yuxuan-xue.com/physic
#SIGGRAPHAsia2025 #AI
Yue Chen retweeted
#InfiniHuman: Infinite 3D Human Generation with Precise Control
How do you want to generate a 3D avatar?
From text description? With clothing images? Or some desired body shape? All can be done at once with InfiniHuman!
🔗Page: yuxuan-xue.com/infini-human/
#SIGGRAPHAsia2025 #AI
