pix2gestalt-weights

cvlab/pix2gestalt-weights

pix2gestalt-weights is a machine learning model from cvlab. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as cc-by-nc-4.0.

Code, Website, arXiv pix2gestalt: Amodal Segmentation by Synthesizing Wholes Ege Ozguroglu<sup1</sup, Ruoshi Liu<sup1</sup, Dídac Surís<sup1</sup, Dian Chen<sup2</sup, Achal Dave<sup2</sup, Pavel Tokmakov<sup2</sup, C…

Downloads · 30 days

Access

Public

Updated Feb 2, 2024

Repo size

15.5 GB

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.ckpt15.5 GB · 100%

At a glance

License: cc-by-nc-4.0
Access: Public
Created: Jan 26, 2024
Updated: Feb 2, 2024
SHA: e10cb0b7

Model card

From the Hugging Face model README

pix2gestalt Model Weights

Code, Website, arXiv
pix2gestalt: Amodal Segmentation by Synthesizing Wholes
Ege Ozguroglu1, Ruoshi Liu1, Dídac Surís1, Dian Chen2, Achal Dave2, Pavel Tokmakov2, Carl Vondrick1 1Columbia University, 2Toyota Research Institute

<div align="left"> <a href="https://gestalt.cs.columbia.edu/"><img height="80%" alt="pix2gestalt" src="https://gestalt.cs.columbia.edu/static/images/teaser/%20pix2gestalt_teaser.jpg"></a> </div> pix2gestalt synthesizes whole objects from only partially visible ones, enabling amodal segmentation, recognition, and 3D reconstruction of occluded objects.

Citation

@misc{ozguroglu2024pix2gestalt,
      title={pix2gestalt: Amodal Segmentation by Synthesizing Wholes}, 
      author={Ege Ozguroglu and Ruoshi Liu and Dídac Surís and Dian Chen and Achal Dave and Pavel Tokmakov and Carl Vondrick},
      year={2024},
      eprint={2401.14398},
      archivePrefix={arXiv},
      primaryClass={cs.CV}
}

Acknowledgement

This research is based on work partially supported by the Toyota Research Institute, the DARPA MCS program under Federal Agreement No. N660011924032, the NSF NRI Award #1925157, and the NSF AI Institute for Artificial and Natural Intelligence Award #2229929. DS is supported by the Microsoft PhD Fellowship.

License: cc-by-nc-4.0
Created: Jan 26, 2024
Updated: Feb 2, 2024