Xiaowei Zhou
@XiaoweiZhou5
Followers
1K
Following
16
Media
2
Statuses
24
Professor of Computer Science at Zhejiang University
Joined June 2021
🚀 Join our Volumetric Video Reconstruction Challenge! 🏆 Top prize of $2500 for the winner.
📢 Submissions are OPEN for the Workshops Program at #SIGGRAPHAsia2025! 🌐 3D Gaussian Splatting 👉 https://t.co/caM6fnufPK 🎥 Volumetric Video 👉 https://t.co/lepgzuANjI 🤖 TriFusion (Humans, Avatars & Robotics) 👉 https://t.co/0u7bziRZxk
#SAworkshops @ruizhen_hu
1
5
23
🚀 We release SpatialTrackerV2: the first feedforward model for dynamic 3D reconstruction and 3D point tracking — all at once! Reconstruct dynamic scenes and predict pixel-wise 3D motion in seconds. 🔗 Webpage: https://t.co/B8widtJ6DT 🔍 Online Demo: https://t.co/sY9iO7wCgT
5
90
466
Tired of short multi-view video datasets? Check out our new SelfCap dataset with up to 10 minutes of 24-cameras high-quality dense view recording at 4K resolution! Data released for our Long Volumetric Video paper: https://t.co/dAxFdKMTCT Dataset link: https://t.co/eX5dIGLjSg
4
29
178
Excited to share our work MatchAnything: We pre-train strong universal image matching models that exhibit remarkable generalizability on unseen multi-modality matching and registration tasks. Project page: https://t.co/o5GisUJ7RT Huggingface Demo: https://t.co/qbz33QBulI
19
160
819
Efficient LoFTR code released! Try it out to get semi-dense matching in real-time: https://t.co/tgeffxOfNa
2
48
414
🚀 Excited to share our breakthrough paper "SpatialTracker: 3D Space Tracking for 2D Pixels" - selected as highlight paper at #CVPR2024! We lifted the dense pixels tracking into 3D space👇 For more details, welcom to check out: https://t.co/DZvEal4nBg
5
90
516
Excited to introduce EasyVolcap, an easy-to-use library to help you develop your own volumetric video systems!
🌟 Introducing EasyVolcap - Our Python & PyTorch library for neural volumetric video! 🛠Features: - Easy to organize volumetric video pipelines - 4D data management system - High-performance 4D viewer - More to come ... 🔗 Code: https://t.co/ltte6r3qLY
#EasyVolcap #4K4D
2
10
100
Excited to share our new work on real-time 4K rendering of volumetric video
4K4D: Real-Time 4D View Synthesis at 4K Resolution Proposes a 4D point cloud representation that supports hardware rasterization and enables unprecedented rendering speed proj: https://t.co/RjQJDGP17f abs: https://t.co/beoCd2KAsI
0
8
98
Check out our SIGGRAPH paper on modeling multiple closely interacting people with few cameras!
Novel View Synthesis of Human Interactions from Sparse Multi-view Videos paper: https://t.co/fYqUt9YlZm github: https://t.co/e7aQpbm0yV
1
22
193
Exciting work from @YimingXie4
PlanarRecon: Real-time 3D Plane Detection and Reconstruction from Posed Monocular Videos abs: https://t.co/5f9rvbIHM6 project page: https://t.co/ppguqFwnuC
0
1
11
Building Brandenburg Gate in hours from Internet photos
Glad to share our work “Neural 3D Reconstruction in the Wild” in SIGGRAPH 2022! We show that with a clever sampling strategy, neural-based 3D reconstruction can be better and faster than COLMAP. Check out the project page at: https://t.co/SEXs4jEl9J.
1
4
43
No CAD models, no instance or category-specific training, all you need is a strong generic feature matcher like SuperGlue or LoFTR. Check out our CVPR 2022 paper on object pose estimation without CAD models!
OnePose: One-Shot Object Pose Estimation without CAD Models abs: https://t.co/1kZPGFXvCJ project page: https://t.co/Sl4sJlzUVF
5
57
434
We revisit the old Manhattan-world constraint in the new era of neural scene representations. Check out our #CVPR2022 oral paper on Neural 3D Scene Reconstruction with the Manhattan-world Assumption: https://t.co/O6wD7b378M
2
28
201
Thank you Qixing @qixing_huang for organizing this fantastic series of 3DGV seminars.
Very nice talk from Xiaowei @XiaoweiZhou5! Recorded video is through the same link: https://t.co/ZSWMfjvHNw The second half was a comprehensive panel discussion.
0
0
6
#3DGV Our next speaker is Xiaowei Zhou (Zhejiang). Talk title: "Towards More Accessible 3D Digitalization of Humans and Scenes". Link: https://t.co/ZSWMfjvHNw Host: Yang Liu (MSRA) Panelists: Yebin Liu (THU) and Lan Xu(ShanghaiTech) 10/27 7:00 pm (PDT)
0
5
33
Amazing LoFTR is in #kornia master branch now! 🥳 Implement state-of-the are image matching methods with 2 lines of code @JiamingSuen ❤️ #CVPR2021 #opensource #computervision #DeepLearning
Excited to share our #CVPR2021 work LoFTR. LoFTR can extract high-quality semi-dense matches even in indistinctive regions with low-textures, motion blur, or repetitive patterns. The project page is at: https://t.co/xBp71thYfu.
2
74
231
As one of my closest mentors and #rolemodel, extremely honoured to be in @KostasPenn's top 5 cited papers (with top 4 in close reach). Thank you Kostas' for your continued support! @geopavlakos @XiaoweiZhou5
1
2
27
I have tried LoFTR for my datasets and it is pure magic. The longer post is going soon, just wanted to say "Wow!" Img-pair1: thermal vs visible + viewpoint change. Img-pair2: light+scale P.S. I just realised that LofTR can stand also for "Lord OF the Rings". Is it intentional?
LoFTR: Detector-Free Local Feature Matching with Transformers @JiamingSuen, Zehong Shen, Yuang Wang, Hujun Bao, Xiaowei Zhou tl;dr: dense local descriptor -> linear transformer matcher (similar to SuperGlue). Everything is in the coarse-to-fine scheme. https://t.co/O8ze2SdTUb
2
22
109
Reconstructing 3D Human Pose by Watching Humans in the Mirror pdf: https://t.co/4AoRvYDIfP abs: https://t.co/L10OpNaFQE project page: https://t.co/0NvY0M2XrD
2
26
110
Excited to share our #CVPR2021 work LoFTR. LoFTR can extract high-quality semi-dense matches even in indistinctive regions with low-textures, motion blur, or repetitive patterns. The project page is at: https://t.co/xBp71thYfu.
7
36
166