AmodalGen3D: Generative Amodal 3D Object Reconstruction from Sparse Unposed Views

• URL: http://arxiv.org/abs/2511.21945v1
• Date: Wed, 26 Nov 2025 22:11:56 GMT
• Title: AmodalGen3D: Generative Amodal 3D Object Reconstruction from Sparse Unposed Views
• Authors: Junwei Zhou, Yu-Wing Tai,
• Abstract summary: Reconstructing 3D objects from a few unposed and partially occluded views is a common yet challenging problem in real-world scenarios.<n>We introduce AmodalGen3D, a generative framework for amodal 3D object reconstruction.<n>By jointly modeling visible and hidden regions, AmodalGen3D faithfully reconstructs 3D objects consistent with sparse-view constraints.
• Score: 37.60004902691764
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Reconstructing 3D objects from a few unposed and partially occluded views is a common yet challenging problem in real-world scenarios, where many object surfaces are never directly observed. Traditional multi-view or inpainting-based approaches struggle under such conditions, often yielding incomplete or geometrically inconsistent reconstructions. We introduce AmodalGen3D, a generative framework for amodal 3D object reconstruction that infers complete, occlusion-free geometry and appearance from arbitrary sparse inputs. The model integrates 2D amodal completion priors with multi-view stereo geometry conditioning, supported by a View-Wise Cross Attention mechanism for sparse-view feature fusion and a Stereo-Conditioned Cross Attention module for unobserved structure inference. By jointly modeling visible and hidden regions, AmodalGen3D faithfully reconstructs 3D objects that are consistent with sparse-view constraints while plausibly hallucinating unseen parts. Experiments on both synthetic and real-world datasets demonstrate that AmodalGen3D achieves superior fidelity and completeness under occlusion-heavy sparse-view settings, addressing a pressing need for object-level 3D scene reconstruction in robotics, AR/VR, and embodied AI applications.

Related papers

• RnG: A Unified Transformer for Complete 3D Modeling from Partial Observations [70.83499963694238]
  RnG (Reconstruction and Generation) is a novel feed-forward Transformer that unifies reconstruction and generation.<n>It reconstructs visible geometry and generates plausible, coherent unseen geometry and appearance.<n>Our method achieves state-of-the-art performance in both generalizable 3D reconstruction and novel view generation.
  arXiv  Detail & Related papers  (2026-03-01T17:25:32Z)
• ReconViaGen: Towards Accurate Multi-view 3D Object Reconstruction via Generation [28.308731720451053]
  We propose ReconViaGen to integrate reconstruction priors into the generative framework.<n>Our experiments demonstrate that our ReconViaGen can reconstruct complete and accurate 3D models consistent with input views in both global structure and local details.
  arXiv  Detail & Related papers  (2025-10-27T13:15:06Z)
• OracleGS: Grounding Generative Priors for Sparse-View Gaussian Splatting [78.70702961852119]
  OracleGS reconciles generative completeness with regressive fidelity for sparse view Gaussian Splatting.<n>Our approach conditions the powerful generative prior on multi-view geometric evidence, filtering hallucinatory artifacts while preserving plausible completions in under-constrained regions.
  arXiv  Detail & Related papers  (2025-09-27T11:19:32Z)
• SCORP: Scene-Consistent Object Refinement via Proxy Generation and Tuning [46.441761732998536]
  We introduce Scene-Consistent Object Refinement via Proxy Generation and Tuning (SCORP)<n>SCORP is a novel 3D enhancement framework that leverages 3D generative priors to recover fine-grained object geometry and appearance under missing views.<n>It achieves consistent gains over recent state-of-the-art baselines on both novel view synthesis and geometry completion tasks.
  arXiv  Detail & Related papers  (2025-06-30T13:26:21Z)
• DeOcc-1-to-3: 3D De-Occlusion from a Single Image via Self-Supervised Multi-View Diffusion [50.90541069907167]
  We propose DeOcc-1-to-3, an end-to-end framework for occlusion-aware multi-view generation.<n>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.
  arXiv  Detail & Related papers  (2025-06-26T17:58:26Z)
• Amodal3R: Amodal 3D Reconstruction from Occluded 2D Images [66.77399370856462]
  Amodal3R is a conditional 3D generative model designed to reconstruct 3D objects from partial observations.<n>It learns to recover full 3D objects even in the presence of occlusions in real scenes.<n>It substantially outperforms existing methods that independently perform 2D amodal completion followed by 3D reconstruction.
  arXiv  Detail & Related papers  (2025-03-17T17:59:01Z)
• Zero-Shot Multi-Object Scene Completion [59.325611678171974]
  We present a 3D scene completion method that recovers the complete geometry of multiple unseen objects in complex scenes from a single RGB-D image. Our method outperforms the current state-of-the-art on both synthetic and real-world datasets.
  arXiv  Detail & Related papers  (2024-03-21T17:59:59Z)
• In-Hand 3D Object Reconstruction from a Monocular RGB Video [17.31419675163019]
  Our work aims to reconstruct a 3D object that is held and rotated by a hand in front of a static RGB camera. Previous methods that use implicit neural representations to recover the geometry of a generic hand-held object from multi-view images achieved compelling results in the visible part of the object.
  arXiv  Detail & Related papers  (2023-12-27T06:19:25Z)
• MOHO: Learning Single-view Hand-held Object Reconstruction with Multi-view Occlusion-Aware Supervision [75.38953287579616]
  We present a novel framework to exploit Multi-view Occlusion-aware supervision from hand-object videos for Hand-held Object reconstruction. We tackle two predominant challenges in such setting: hand-induced occlusion and object's self-occlusion. Experiments on HO3D and DexYCB datasets demonstrate 2D-supervised MOHO gains superior results against 3D-supervised methods by a large margin.
  arXiv  Detail & Related papers  (2023-10-18T03:57:06Z)
• Anything-3D: Towards Single-view Anything Reconstruction in the Wild [61.090129285205805]
  We introduce Anything-3D, a methodical framework that ingeniously combines a series of visual-language models and the Segment-Anything object segmentation model. Our approach employs a BLIP model to generate textural descriptions, utilize the Segment-Anything model for the effective extraction of objects of interest, and leverages a text-to-image diffusion model to lift object into a neural radiance field.
  arXiv  Detail & Related papers  (2023-04-19T16:39:51Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.