Basile Van Hoorick (@basilevanh) - Twitter Profili

Sabitlenmiş 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)

English

5

31

136

33.5K

Basile Van Hoorick retweetledi

Junjie Ye@JunjieYe9·18 Şub

🚀 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/

English

1

3

18

3.8K

Basile Van Hoorick@basilevanh·26 Eyl

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 🎉

Basile Van Hoorick@basilevanh

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)

English

3

26

2.4K

Basile Van Hoorick@basilevanh·20 Haz

@DoctorJosh

QME

0

1

66

Josh Bongard@DoctorJosh·12 Haz

Want to help with #AIDesignedBots? 1. Go to bit.ly/3RkEZ3A to design your bot. 2. Follow the instructions there. 3. Forward this tweet on.

English

65

39

90

10.8K

Basile Van Hoorick@basilevanh·24 May

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)

English

2

0

8

569

Basile Van Hoorick@basilevanh·24 May

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)

English

2

0

7

467

Basile Van Hoorick@basilevanh·24 May

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)

English

5

31

136

33.5K

Basile Van Hoorick@basilevanh·4 Eki

Feel free to come by our poster (number 104 in Nord room) Thursday morning starting at 10:30am! 😃

Basile Van Hoorick@basilevanh

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)

English

0

3

16

2.6K

Basile Van Hoorick@basilevanh·24 Eyl

Check out our #zero123 live demo here! huggingface.co/spaces/cvlab/z… Big shoutout to collaborators: @ruoshi_liu (first author), @ChrisWu6080, @ptokmakov, @ZakharovSergeyN, and @cvondrick. Hope to see you all next week at ICCV! ;-) 🧵(4/4)

English

0

1

2

422

Basile Van Hoorick@basilevanh·24 Eyl

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)

English

1

0

3

448

Basile Van Hoorick@basilevanh·24 Eyl

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)

English

3

41

202

21.3K

Basile Van Hoorick@basilevanh·21 Haz

Come by poster number 138 at #CVPR2023 tomorrow afternoon at 4:30 pm! 🎉

Basile Van Hoorick@basilevanh

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)

English

0

1

2

891

Basile Van Hoorick@basilevanh·12 Haz

After some polishing, the code has been published on GitHub ;-) github.com/basilevh/tcow

Basile Van Hoorick@basilevanh

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)

English

0

1

116

Basile Van Hoorick@basilevanh·5 May

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)

English

0

1

0

177

Basile Van Hoorick@basilevanh·5 May

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)

English

1

0

127

Basile Van Hoorick@basilevanh·5 May

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)

English

2

17

68

7.4K

Basile Van Hoorick

Keşfet