USR-Drive: Unified Driving Scene Representation via Joint Denoising of 3D Gaussians and Boxes

• URL: http://arxiv.org/abs/2608.19036v1
• Date: Wed, 19 Aug 2026 15:29:06 GMT
• Title: USR-Drive: Unified Driving Scene Representation via Joint Denoising of 3D Gaussians and Boxes
• Abstract summary: Spatial representation learning for autonomous driving aims to map raw visual signals into structured 3D scene representations.<n>Existing methods treat dynamic reconstruction and instance-level perception as separate tasks.<n>We propose USR-Drive, a unified conditional generative framework that recovers dense dynamic geometry and instance-level object layouts within a shared scene representation.
• Score: 57.4583999658488
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Spatial representation learning for autonomous driving aims to map raw visual signals into structured 3D scene representations, where object-centric bounding boxes and rendering-oriented 3D primitives (\eg, 3D Gaussians) serve as two distinct yet highly complementary levels for scene understanding. Existing methods typically treat dynamic reconstruction and instance-level perception as separate tasks, despite their shared goal of estimating the underlying 3D world state. As a result, dynamic reconstruction is under-constrained while 3D detection lacks geometric grounding. To address this gap, we propose USR-Drive, a unified conditional generative framework that, given only posed multi-view driving videos, jointly recovers dense dynamic geometry and instance-level object layouts within a shared scene representation. Specifically, USR-Drive represents dense Gaussian primitives and sparse 3D bounding boxes as two aligned latent token streams and jointly denoises them with a unified multi-modal diffusion Transformer. Unlike prior paradigms that use boxes as external conditions or predict them with detached modules, USR-Drive treats them as mutually constrained state variables with a Unified Positional Encoding (UPE) that aligns heterogeneous tokens within a shared metric spatiotemporal coordinate. Via such unified representation and generative framework, the two modalities reinforce each other: geometry supplies dense metric evidence for box prediction, while boxes provide instance-level structural priors that help preserve spatial consistency and reduce ambiguity in sequential 3D geometric representation. Our approach successfully delivers state-of-the-art results for both dynamic reconstruction and 3D detection on the nuScenes and VKitti datasets.

Related papers

• Geometry Without Coordinates: LiDAR Diffusion as a 3D Feature Bridge [0.0]
  We introduce a LiDAR-conditioned diffusion model trained on pseudo-labels from off-the-shelf 2D foundation models.<n>Because the model is conditioned on LiDAR, both its outputs and its intermediate UNet features can be projected back onto the input point cloud.<n>We study this representation directly in point-cloud space, explicitly excluding raw spatial coordinates.
  arXiv  Detail & Related papers  (2026-09-09T15:26:35Z)
• Geometry-Grounded Unified 3D Perception for Autonomous Driving [36.11730832045922]
  Camera-based autonomous driving perception requires a shared representation that preserves metric 3D structure across synchronized multi-camera streams.<n>We present a Geometry-grounded Unified 3D Perception framework that adapts the reconstruction-oriented latent of VGGT to calibrated, streaming driving scenes.
  arXiv  Detail & Related papers  (2026-08-13T12:17:50Z)
• 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)
• SpatialFly: Geometry-Guided Representation Alignment for UAV Vision-and-Language Navigation in Urban Environments [49.966170814478915]
  We propose a geometry-guided spatial representation framework for UAV VLN.<n>Running on RGB observations without explicit 3D reconstruction, SpatialFly introduces a geometry-guided 2D representation alignment mechanism.<n> Experimental results show that SpatialFly consistently outperforms state-of-the-art UAV VLN baselines across both seen and unseen environments.
  arXiv  Detail & Related papers  (2026-03-22T03:56:58Z)
• Interact3D: Compositional 3D Generation of Interactive Objects [31.12099147294145]
  We present a novel framework designed to generate physically plausible interacting 3D compositional objects.<n>Our approach first leverages advanced generative priors to curate high-quality individual assets.<n>To physically compose these assets, we then introduce a robust two-stage composition pipeline.
  arXiv  Detail & Related papers  (2026-03-17T03:21:06Z)
• Hierarchical Collaborative Fusion for 3D Instance-aware Referring Expression Segmentation [91.2768117730855]
  Generalised 3D Referring Expression (3D-GRES) localizes objects in 3D scenes based on natural language, even when descriptions match multiple or zero targets.<n>Existing methods rely solely on sparse point clouds, lacking rich visual semantics for fine-grained descriptions.<n>We propose HCF-RES, a multi-modal framework with two key innovations.
  arXiv  Detail & Related papers  (2026-03-06T13:09:29Z)
• IGGT: Instance-Grounded Geometry Transformer for Semantic 3D Reconstruction [82.53307702809606]
  Humans naturally perceive the geometric structure and semantic content of a 3D world as intertwined dimensions.<n>We propose InstanceGrounded Geometry Transformer (IGGT) to unify the knowledge for both spatial reconstruction and instance-level contextual understanding.
  arXiv  Detail & Related papers  (2025-10-26T14:57:44Z)
• Cross-Modal Geometric Hierarchy Fusion: An Implicit-Submap Driven Framework for Resilient 3D Place Recognition [9.411542547451193]
  We propose a novel framework that redefines 3D place recognition through density-agnostic geometric reasoning.<n>Specifically, we introduce an implicit 3D representation based on elastic points, which is immune to the interference of original scene point cloud density.<n>With the aid of these two types of information, we obtain descriptors that fuse geometric information from both bird's-eye view and 3D segment perspectives.
  arXiv  Detail & Related papers  (2025-06-17T07:04:07Z)
• NEAT: Distilling 3D Wireframes from Neural Attraction Fields [52.90572335390092]
  This paper studies the problem of structured lineframe junctions using 3D reconstruction segments andFocusing junctions. ProjectNEAT enjoys the joint neural fields and view without crossart matching from scratch.
  arXiv  Detail & Related papers  (2023-07-14T07:25:47Z)

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.