Joseph Tung
@jtung.bsky.social
CS PhD Student @ NYU doing 3D computer vision
https://jot-jt.github.io/
https://jot-jt.github.io/
Thanks Zhenjun for sharing!
Dynamic Camera Poses and Where to Find Them
Chris Rockwell, @jtung.bsky.social, Tsung-Yi Lin, Ming-Yu Liu, David F. Fouhey, Chen-Hsuan Lin
tl;dr: a large-scale dataset of dynamic Internet videos annotated with camera poses
arxiv.org/abs/2504.17788
Chris Rockwell, @jtung.bsky.social, Tsung-Yi Lin, Ming-Yu Liu, David F. Fouhey, Chen-Hsuan Lin
tl;dr: a large-scale dataset of dynamic Internet videos annotated with camera poses
arxiv.org/abs/2504.17788
April 25, 2025 at 12:21 PM
Thanks Zhenjun for sharing!
Reposted by Joseph Tung
Late to post, but excited to introduce CUT3R!
An online 3D reasoning framework for many 3D tasks directly from just RGB. For static or dynamic scenes. Video or image collections, all in one!
Project Page: cut3r.github.io
Code and Model: github.com/CUT3R/CUT3R
An online 3D reasoning framework for many 3D tasks directly from just RGB. For static or dynamic scenes. Video or image collections, all in one!
Project Page: cut3r.github.io
Code and Model: github.com/CUT3R/CUT3R
February 18, 2025 at 5:03 PM
Late to post, but excited to introduce CUT3R!
An online 3D reasoning framework for many 3D tasks directly from just RGB. For static or dynamic scenes. Video or image collections, all in one!
Project Page: cut3r.github.io
Code and Model: github.com/CUT3R/CUT3R
An online 3D reasoning framework for many 3D tasks directly from just RGB. For static or dynamic scenes. Video or image collections, all in one!
Project Page: cut3r.github.io
Code and Model: github.com/CUT3R/CUT3R
Reposted by Joseph Tung
🤔Can Generative Video Models Help Pose Estimation?
✅Yes!
We find that generative video models can hallucinate plausible intermediate frames that provide useful context for pose estimators (e.g. DUSt3R), especially for images with little to no overlap.
🔗 inter-pose.github.io
✅Yes!
We find that generative video models can hallucinate plausible intermediate frames that provide useful context for pose estimators (e.g. DUSt3R), especially for images with little to no overlap.
🔗 inter-pose.github.io
December 23, 2024 at 5:44 PM
🤔Can Generative Video Models Help Pose Estimation?
✅Yes!
We find that generative video models can hallucinate plausible intermediate frames that provide useful context for pose estimators (e.g. DUSt3R), especially for images with little to no overlap.
🔗 inter-pose.github.io
✅Yes!
We find that generative video models can hallucinate plausible intermediate frames that provide useful context for pose estimators (e.g. DUSt3R), especially for images with little to no overlap.
🔗 inter-pose.github.io
Reposted by Joseph Tung
Introducing 👀Stereo4D👀
A method for mining 4D from internet stereo videos. It enables large-scale, high-quality, dynamic, *metric* 3D reconstructions, with camera poses and long-term 3D motion trajectories.
We used Stereo4D to make a dataset of over 100k real-world 4D scenes.
A method for mining 4D from internet stereo videos. It enables large-scale, high-quality, dynamic, *metric* 3D reconstructions, with camera poses and long-term 3D motion trajectories.
We used Stereo4D to make a dataset of over 100k real-world 4D scenes.
December 13, 2024 at 3:13 AM
Introducing 👀Stereo4D👀
A method for mining 4D from internet stereo videos. It enables large-scale, high-quality, dynamic, *metric* 3D reconstructions, with camera poses and long-term 3D motion trajectories.
We used Stereo4D to make a dataset of over 100k real-world 4D scenes.
A method for mining 4D from internet stereo videos. It enables large-scale, high-quality, dynamic, *metric* 3D reconstructions, with camera poses and long-term 3D motion trajectories.
We used Stereo4D to make a dataset of over 100k real-world 4D scenes.
Reposted by Joseph Tung
Doppelgangers++: Improved Visual Disambiguation with Geometric 3D Features
Yuanbo Xiangli, Ruojin Cai, Hanyu Chen, Jeffrey Byrne,
@snavely.bsky.social
tl;dr: new dataset (55K pairs) + Mast3r == PROFIT
arxiv.org/abs/2412.05826
December 10, 2024 at 10:19 AM
Doppelgangers++: Improved Visual Disambiguation with Geometric 3D Features
Yuanbo Xiangli, Ruojin Cai, Hanyu Chen, Jeffrey Byrne,
@snavely.bsky.social
tl;dr: new dataset (55K pairs) + Mast3r == PROFIT
arxiv.org/abs/2412.05826