PixWorld: Unifying 3D Scene Generation and Reconstruction in Pixel Space

• URL: http://arxiv.org/abs/2607.05373v1
• Date: Mon, 06 Jul 2026 17:51:00 GMT
• Title: PixWorld: Unifying 3D Scene Generation and Reconstruction in Pixel Space
• Abstract summary: 3D reconstruction and generation are commonly tackled by separate paradigms.<n>Recent works attempt to unify them in latent space, but with notable drawbacks.<n>We introduce PixWorld, a single model that jointly addresses 3D reconstruction and generation.
• Score: 25.621179726094056
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 3D reconstruction and generation are commonly tackled by separate paradigms: pixel-based regression for reconstruction, and latent diffusion for generation. Recent works attempt to unify them in latent space, but with notable drawbacks: the diffusion objective is defined on latent features rather than the underlying 3D representation, and both branches suffer from information loss introduced by latent encoding, while requiring a pretrained Variational Autoencoder (VAE) or Representation Autoencoder (RAE). In this paper, we reformulate these two tasks under a unified pixel-space diffusion paradigm and introduce PixWorld, a single model that jointly addresses 3D reconstruction and generation. By supervising diffusion directly on rendered images, PixWorld removes the above limitations and aligns optimization with 3D scene fidelity. Beyond photometric and perceptual supervision that operates at the 2D image level and lacks 3D geometric awareness, we further introduce a geometry perception loss that aligns rendered views with their ground truth in the geometry-aware feature space of a pretrained 3D foundation model, providing 3D structural supervision. PixWorld consistently outperforms prior latent-space generation methods and matches state-of-the-art reconstruction methods, demonstrating the superiority of a unified pixel-space approach.

Related papers

• Pano3D: Unified 3D Reconstruction and Panoptic Segmentation [68.18993232814061]
  We introduce an approach that performs 3D reconstruction and 3D panoptic segmentation in a unified framework.<n>We build on existing 3D reconstruction models and augment them with a set-based mask decoder.<n>Our method achieves state-of-the-art performance in 3D panoptic segmentation across ScanNet, ScanNet200, and ScanNet++ datasets.
  arXiv  Detail & Related papers  (2026-06-12T09:43:13Z)
• Native3D: End-to-End 3D Scene Generation via Unified Mesh-Texture Modeling and Semantic Alignment [8.98466538269363]
  Native3D is the first end-to-end 3D scene generation framework that completely bypasses 2D intermediate representations.<n>We propose a unified mesh-texture joint representation that simultaneously models both geometric structures and texture features through a Transformer-based scene encoder.
  arXiv  Detail & Related papers  (2026-06-05T10:13:17Z)
• Learning 3D Representations for Spatial Intelligence from Unposed Multi-View Images [81.94999489820974]
  UniSplat is a feed-forward framework for learning 3D representations from unposed multi-view images.<n>We introduce a dual-masking strategy that strengthens geometry induction in the encoder.<n>Second, we develop a coarse-to-fine Gaussian splatting strategy that reduces appearance-semantics inconsistencies.<n>Third, we introduce a pose-conditioned recalibration mechanism that interrelates predicted 3D point and semantic maps into the image plane.
  arXiv  Detail & Related papers  (2026-04-12T10:36:18Z)
• OneWorld: Taming Scene Generation with 3D Unified Representation Autoencoder [90.8453349494245]
  We present OneWorld, a framework that performs diffusion directly within a coherent 3D representation space.<n>OneWorld generates high-quality 3D scenes with superior cross-view consistency compared to state-of-the-art 2D-based methods.
  arXiv  Detail & Related papers  (2026-03-17T03:43:37Z)
• NOVA3R: Non-pixel-aligned Visual Transformer for Amodal 3D Reconstruction [99.52487968452198]
  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.
  arXiv  Detail & Related papers  (2026-03-04T15:36:25Z)
• E-RayZer: Self-supervised 3D Reconstruction as Spatial Visual Pre-training [55.61379509038588]
  We present E-RayZer, a self-supervised large 3D Vision model that learns truly 3D-aware representations directly from unlabeled images.<n>E-RayZer operates directly in 3D space, performing self-supervised 3D reconstruction with Explicit geometry.
  arXiv  Detail & Related papers  (2025-12-11T18:59:53Z)
• GEOcc: Geometrically Enhanced 3D Occupancy Network with Implicit-Explicit Depth Fusion and Contextual Self-Supervision [49.839374549646884]
  This paper presents GEOcc, a Geometric-Enhanced Occupancy network tailored for vision-only surround-view perception.<n>Our approach achieves State-Of-The-Art performance on the Occ3D-nuScenes dataset with the least image resolution needed and the most weightless image backbone.
  arXiv  Detail & Related papers  (2024-05-17T07:31:20Z)
• LIST: Learning Implicitly from Spatial Transformers for Single-View 3D Reconstruction [5.107705550575662]
  List is a novel neural architecture that leverages local and global image features to reconstruct geometric and topological structure of a 3D object from a single image. We show the superiority of our model in reconstructing 3D objects from both synthetic and real-world images against the state of the art.
  arXiv  Detail & Related papers  (2023-07-23T01:01:27Z)

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.