NOVA3R: Non-pixel-aligned Visual Transformer for Amodal 3D Reconstruction

• URL: http://arxiv.org/abs/2603.04179v2
• Date: Thu, 05 Mar 2026 14:25:25 GMT
• Title: NOVA3R: Non-pixel-aligned Visual Transformer for Amodal 3D Reconstruction
• Authors: Weirong Chen, Chuanxia Zheng, Ganlin Zhang, Andrea Vedaldi, Daniel Cremers,
• Abstract summary: NOVA3R is an effective approach for non-pixel-aligned 3D reconstruction from a set of unposed images in a feed-forward manner.<n>It produces physically plausible geometry with fewer duplicated structures in overlapping regions.<n>It outperforms state-of-the-art methods in terms of reconstruction accuracy and completeness.
• Score: 99.52487968452198
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We present NOVA3R, an effective approach for non-pixel-aligned 3D reconstruction from a set of unposed images in a feed-forward manner. Unlike pixel-aligned methods that tie geometry to per-ray predictions, our formulation learns a global, view-agnostic scene representation that decouples reconstruction from pixel alignment. This addresses two key limitations in pixel-aligned 3D: (1) it recovers both visible and invisible points with a complete scene representation, and (2) it produces physically plausible geometry with fewer duplicated structures in overlapping regions. To achieve this, we introduce a scene-token mechanism that aggregates information across unposed images and a diffusion-based 3D decoder that reconstructs complete, non-pixel-aligned point clouds. Extensive experiments on both scene-level and object-level datasets demonstrate that NOVA3R outperforms state-of-the-art methods in terms of reconstruction accuracy and completeness.

Related papers

• PlückeRF: A Line-based 3D Representation for Few-view Reconstruction [14.344029183977046]
  We propose a few-view reconstruction model that more effectively harnesses multi-view information.<n>Our approach introduces a simple mechanism that connects the 3D representation with pixel rays from the input views.<n>We demonstrate improvements in reconstruction quality over the equivalent triplane representation.
  arXiv  Detail & Related papers  (2025-06-04T08:45:48Z)
• HORT: Monocular Hand-held Objects Reconstruction with Transformers [61.36376511119355]
  Reconstructing hand-held objects in 3D from monocular images is a significant challenge in computer vision.<n>We propose a transformer-based model to efficiently reconstruct dense 3D point clouds of hand-held objects.<n>Our method achieves state-of-the-art accuracy with much faster inference speed, while generalizing well to in-the-wild images.
  arXiv  Detail & Related papers  (2025-03-27T09:45:09Z)
• 3DFIRES: Few Image 3D REconstruction for Scenes with Hidden Surface [8.824340350342512]
  3DFIRES is a novel system for scene-level 3D reconstruction from posed images. We show it matches the efficacy of single-view reconstruction methods with only one input.
  arXiv  Detail & Related papers  (2024-03-13T17:59:50Z)
• 2L3: Lifting Imperfect Generated 2D Images into Accurate 3D [16.66666619143761]
  Multi-view (MV) 3D reconstruction is a promising solution to fuse generated MV images into consistent 3D objects. However, the generated images usually suffer from inconsistent lighting, misaligned geometry, and sparse views, leading to poor reconstruction quality. We present a novel 3D reconstruction framework that leverages intrinsic decomposition guidance, transient-mono prior guidance, and view augmentation to cope with the three issues.
  arXiv  Detail & Related papers  (2024-01-29T02:30:31Z)
• Single-view 3D Scene Reconstruction with High-fidelity Shape and Texture [47.44029968307207]
  We propose a novel framework for simultaneous high-fidelity recovery of object shapes and textures from single-view images. Our approach utilizes the proposed Single-view neural implicit Shape and Radiance field (SSR) representations to leverage both explicit 3D shape supervision and volume rendering. A distinctive feature of our framework is its ability to generate fine-grained textured meshes while seamlessly integrating rendering capabilities into the single-view 3D reconstruction model.
  arXiv  Detail & Related papers  (2023-11-01T11:46:15Z)
• Flattening-Net: Deep Regular 2D Representation for 3D Point Cloud Analysis [66.49788145564004]
  We present an unsupervised deep neural architecture called Flattening-Net to represent irregular 3D point clouds of arbitrary geometry and topology. Our methods perform favorably against the current state-of-the-art competitors.
  arXiv  Detail & Related papers  (2022-12-17T15:05:25Z)
• Vision Transformer for NeRF-Based View Synthesis from a Single Input Image [49.956005709863355]
  We propose to leverage both the global and local features to form an expressive 3D representation. To synthesize a novel view, we train a multilayer perceptron (MLP) network conditioned on the learned 3D representation to perform volume rendering. Our method can render novel views from only a single input image and generalize across multiple object categories using a single model.
  arXiv  Detail & Related papers  (2022-07-12T17:52:04Z)
• Neural 3D Reconstruction in the Wild [86.6264706256377]
  We introduce a new method that enables efficient and accurate surface reconstruction from Internet photo collections. We present a new benchmark and protocol for evaluating reconstruction performance on such in-the-wild scenes.
  arXiv  Detail & Related papers  (2022-05-25T17:59:53Z)
• GaussiGAN: Controllable Image Synthesis with 3D Gaussians from Unposed Silhouettes [48.642181362172906]
  We present an algorithm that learns a coarse 3D representation of objects from unposed multi-view 2D mask supervision. In contrast to existing voxel-based methods for unposed object reconstruction, our approach learns to represent the generated shape and pose. We show results on synthetic datasets with realistic lighting, and demonstrate object insertion with interactive posing.
  arXiv  Detail & Related papers  (2021-06-24T17:47:58Z)

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.