cs.CVNov 13, 2026

Open-World Scene Deocclusion

Authors: K. M. S. J. Kumarasinghe, Neil A. Dodgson, Fang-Lue Zhang

Organizations: Victoria University of Wellington · University of New South Wales

Abstract

Recovering the complete appearance of occluded objects from a single image is a fundamental problem for scene understanding and image editing. Real-world scenes are challenging due to clutter, complex spatial occlusions, and diverse object categories. Existing methods often struggle when occlusion involves background surfaces or objects that are not explicitly detected, and fail to resolve the cyclic occlusion dependencies that frequently occur in natural scenes. We introduce a training-free, open-world scene deocclusion framework that recovers the full amodal appearance of detected or user-selected objects from a single RGB image, decomposing the scene into depth-ordered RGBA layers that are geometrically plausible, semantically faithful, and visually consistent with the visible scene. Extensive experiments show that our approach improves scene-level deocclusion, producing coherent and realistic reconstructions in real-world settings. Code will be available on the project page: https://sashjk.github.io/owsd/

Figures & tables

Explore similar work

CardsList
  1. Unravel: Recovering an Interactive 3D Scene from a Single Image

    Oct 12, 2026Hui Shan, Keyang Luo, Binjia Zhou +11Object-Centric 3D ReconstructionImage-to-3D Scene Generation

  2. Vision-Reasoning-Guided Occlusion Removal from Light Fields

    Jun 18, 2026Mohamed Youssef, Oliver Bimberlight field imaging

  3. Towards Reconstructing and Recognizing Objects behind Fragmented Occlusion using Video

    Nov 9, 2026Roman Pflugfelder, Michael Lindenbaum, Daniel CremersOcclusion Reasoning