Pinned Tweet
Excited to share our new paper on large-angle monocular dynamic novel view synthesis! Given a single RGB video, we propose a method that can imagine what that scene would look like from any other viewpoint.
Website: gcd.cs.columbia.edu/
Paper: arxiv.org/abs/2405.14868
🧵(1/5)
Basile Van Hoorick retweeted
🚀 𝑨𝒏𝒄𝒉𝒐𝒓𝑫𝒓𝒆𝒂𝒎 accepted to #ICRA2026!
Video diffusion often "hallucinates" robot motion. We ground diffusion in kinematics to synthesize high-fidelity, embodiment-consistent training data.
📖 Paper: arxiv.org/pdf/2512.11797
🌐 Project: junjieye.com/AnchorDream/
We are grateful to be awarded an oral presentation -- please come by Wed 10/2 at 1:30pm (I believe we are the first talk in the oral session) as well as the poster session afterward (number 156) at 4:30pm! #ECCV2024 🎉
Excited to share our new paper on large-angle monocular dynamic novel view synthesis! Given a single RGB video, we propose a method that can imagine what that scene would look like from any other viewpoint.
Website: gcd.cs.columbia.edu/
Paper: arxiv.org/abs/2405.14868
🧵(1/5)
Apart from robotics and related scenes, it also works quite well on driving scenarios! In general, we believe our framework can help unlock powerful applications in rich dynamic scene understanding, perception for embodied AI, and interactive 3D video viewing.
🧵(4/5)
Visit our webpage at gcd.cs.columbia.edu for many more results! Datasets, code, and pretrained models coming soon.
Many thanks to my amazing collaborators: @ChrisWu6080, @EgeOzguroglu, @KyleSargentAI, @ruoshi_liu, @ptokmakov, @achalddave, Changxi Zheng, @cvondrick
🧵(5/5)
Feel free to come by our poster (number 104 in Nord room) Thursday morning starting at 10:30am! 😃
Happy to share our #ICCV2023 paper on 3D reconstruction from a single image!
In Zero-1-to-3, we teach diffusion models to control the camera viewpoint, which enables novel view synthesis applications.
Website: zero123.cs.columbia.edu
Paper: arxiv.org/abs/2303.11328
🧵(1/n)
Happy to share our #ICCV2023 paper on 3D reconstruction from a single image!
In Zero-1-to-3, we teach diffusion models to control the camera viewpoint, which enables novel view synthesis applications.
Website: zero123.cs.columbia.edu
Paper: arxiv.org/abs/2303.11328
🧵(1/n)
Specifically, we finetune Stable Diffusion, which already has useful 2D image priors thanks to being trained on billion-scale data.
This pipeline allows us to successfully achieve strong zero-shot performance on objects with complex geometry and artistic styles.
🧵(3/n)
Check out our #zero123 live demo here! huggingface.co/spaces/cvlab/…
Big shoutout to collaborators: @ruoshi_liu (first author), @ChrisWu6080, @ptokmakov, @ZakharovSergeyN, and @cvondrick.
Hope to see you all next week at ICCV! ;-)
🧵(4/4)
Come by poster number 138 at #CVPR2023 tomorrow afternoon at 4:30 pm! 🎉
Excited to share our #CVPR2023 paper on tracking with object permanence in video!
In TCOW, we propose both a model and a dataset for localizing objects regardless of their visibility.
Website: tcow.cs.columbia.edu
Paper: arxiv.org/abs/2305.03052
🧵 (1/n)
After some polishing, the code has been published on GitHub ;-)
github.com/basilevh/tcow
Excited to share our #CVPR2023 paper on tracking with object permanence in video!
In TCOW, we propose both a model and a dataset for localizing objects regardless of their visibility.
Website: tcow.cs.columbia.edu
Paper: arxiv.org/abs/2305.03052
🧵 (1/n)
Excited to share our #CVPR2023 paper on tracking with object permanence in video!
In TCOW, we propose both a model and a dataset for localizing objects regardless of their visibility.
Website: tcow.cs.columbia.edu
Paper: arxiv.org/abs/2305.03052
🧵 (1/n)
Visit our project webpage at tcow.cs.columbia.edu for many more results, as well as links to the datasets, code, and pretrained models!
Joint work with @ptokmakov, Simon Stent, Jie Li, and @cvondrick.
🧵 (6/n)
P.S. Also check out our earlier related work on Revealing Occlusions with 4D Neural Fields (arxiv.org/abs/2204.10916)! This paper is essentially about video-to-4D generation, but requires depth input. On the other hand, we demonstrate that TCOW works in the wild too.
🧵 (7/7)