pix2gestalt: Amodal Segmentation by Synthesizing Wholes

Ege Ozguroglu, Ruoshi Liu, Didac Suris, Dian Chen, Achal Dave, Pavel Tokmakov, Carl Vondrick

pix2gestalt: Amodal Segmentation by Synthesizing Wholes: 10 upvotes on Hugging Face Daily Papers, #11 of 14 papers on 2024-01-26. Day-by-day upvote history.

We introduce pix2gestalt, a framework for zero-shot amodal segmentation, which learns to estimate the shape and appearance of whole objects that are only partially visible behind occlusions. By capitalizing on large-scale diffusion models and transferring their representations to this task, we learn a conditional diffusion model for reconstructing whole objects in challenging zero-shot cases, including examples that break natural and physical priors, such as art. As training data, we use a synthetically curated dataset containing occluded objects paired with their whole counterparts. Experiments show that our approach outperforms supervised baselines on established benchmarks. Our model can furthermore be used to significantly improve the performance of existing object recognition and 3D reconstruction methods in the presence of occlusions.

Paper page on Hugging Face · arXiv

Data: hysts-bot-data/daily-papers-stats and the Daily Papers API. Open data: tardellirs/paper-pulse-data. Sister project: Model Pulse, the download history of every model on the Hub.