DeOcc-1-to-3: 3D De-Occlusion from a Single Image via Self-Supervised Multi-View Diffusion

TL;DR

DeOcc-1-to-3 introduces a self-supervised, occlusion-aware multi-view synthesis framework that enables accurate 3D object reconstruction from a single occluded image, outperforming prior methods that assume fully visible inputs.

Contribution

The paper presents the first end-to-end, self-supervised approach for occlusion-aware multi-view generation from a single image, eliminating the need for inpainting or manual annotations.

Findings

Achieves structurally consistent novel views from occluded images

Enables reliable 3D reconstruction without prior inpainting

Introduces a new benchmark for occlusion-aware reconstruction

Abstract

Reconstructing 3D objects from a single image remains challenging, especially under real-world occlusions. While recent diffusion-based view synthesis models can generate consistent novel views from a single RGB image, they typically assume fully visible inputs and fail when parts of the object are occluded, resulting in degraded 3D reconstruction quality. We propose DeOcc-1-to-3, an end-to-end framework for occlusion-aware multi-view generation that synthesizes six structurally consistent novel views directly from a single occluded image, enabling reliable 3D reconstruction without prior inpainting or manual annotations. Our self-supervised training pipeline leverages occluded-unoccluded image pairs and pseudo-ground-truth views to teach the model structure-aware completion and view consistency. Without modifying the original architecture, we fully fine-tune the view synthesis model to jointly learn completion and multi-view generation. Additionally, we introduce the first benchmark for occlusion-aware reconstruction, covering diverse occlusion levels, object categories, and masking patterns, providing a standardized protocol for future evaluation.