Skip to yearly menu bar Skip to main content


pix2gestalt: Amodal Segmentation by Synthesizing Wholes

Ege Ozguroglu · Ruoshi Liu · Dídac Surís · Dian Chen · Achal Dave · Pavel Tokmakov · Carl Vondrick

Arch 4A-E Poster #364
award Highlight
[ ]
Wed 19 Jun 10:30 a.m. PDT — noon PDT


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.

Live content is unavailable. Log in and register to view live content