DriveFix: Spatio-Temporally Coherent Driving Scene Restoration

• URL: http://arxiv.org/abs/2603.16306v1
• Date: Tue, 17 Mar 2026 09:41:14 GMT
• Title: DriveFix: Spatio-Temporally Coherent Driving Scene Restoration
• Abstract summary: DriveFix is a novel multi-view restoration framework for autonomous driving scenes.<n>Our approach employs an interleaved diffusion transformer architecture with specialized blocks to model both temporal and cross-camera spatial coherence.<n>It enforces that the restored views adhere to a unified 3D geometry, significantly reducing artifacts.
• Score: 42.359886606034536
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Recent advancements in 4D scene reconstruction, particularly those leveraging diffusion priors, have shown promise for novel view synthesis in autonomous driving. However, these methods often process frames independently or in a view-by-view manner, leading to a critical lack of spatio-temporal synergy. This results in spatial misalignment across cameras and temporal drift in sequences. We propose DriveFix, a novel multi-view restoration framework that ensures spatio-temporal coherence for driving scenes. Our approach employs an interleaved diffusion transformer architecture with specialized blocks to explicitly model both temporal dependencies and cross-camera spatial consistency. By conditioning the generation on historical context and integrating geometry-aware training losses, DriveFix enforces that the restored views adhere to a unified 3D geometry. This enables the consistent propagation of high-fidelity textures and significantly reduces artifacts. Extensive evaluations on the Waymo, nuScenes, and PandaSet datasets demonstrate that DriveFix achieves state-of-the-art performance in both reconstruction and novel view synthesis, marking a substantial step toward robust 4D world modeling for real-world deployment.

Related papers

• PRG-Fusion: Orchestrating Generative Priors with Reconstruction Evidence for Driving View Synthesis [16.51293833344591]
  We propose PRG-Fusion, a framework for driving view synthesis that uses reconstruction evidence to orchestrate generative priors across regions.<n>Specifically, we extract region-wise reconstruction evidence from reconstructed driving scenes and convert it into Preserve, Repair, and Generate (PRG) labels.<n>We then follow a two-stage training paradigm, first establish geometric control from sparse LiDAR projections and subsequently learning appearance control from dense 3DGS.
  arXiv  Detail & Related papers  (2026-09-07T02:34:51Z)
• InfiniVerse: Occupancy Guided Unbounded Scene Generation for Autonomous Driving [70.7737035270887]
  We introduce InfiniVerse, a unified pipeline for synthesis of dynamic urban scenes from a single frame.<n>InfiniVerse achieves state-of-the-art performance with a FID of 6.4 and FVD of 67.97, significantly outperforming existing benchmarks in both duration and stability.
  arXiv  Detail & Related papers  (2026-06-30T04:08:22Z)
• AnyRecon: Arbitrary-View 3D Reconstruction with Video Diffusion Model [29.087865646035695]
  Sparse-view 3D reconstruction is essential for modeling scenes from casual captures, but remain challenging for non-generative reconstruction.<n>We propose AnyRecon, a scalable framework for reconstruction from arbitrary and unordered sparse inputs.<n>Experiments demonstrate robust and scalable reconstruction across irregular inputs, large viewpoint gaps, and long trajectories.
  arXiv  Detail & Related papers  (2026-04-21T17:59:47Z)
• Lyra 2.0: Explorable Generative 3D Worlds [77.45279013687427]
  We present Lyra 2.0, a framework for generating persistent, explorable 3D worlds at scale.<n>To address spatial forgetting, we maintain per-frame 3D geometry and use it solely for information routing.<n>We train with self-augmented histories that expose the model to its own degraded outputs, teaching it to correct drift rather than propagate it.
  arXiv  Detail & Related papers  (2026-04-14T17:59:44Z)
• RAYNOVA: Scale-Temporal Autoregressive World Modeling in Ray Space [51.441415833480505]
  RAYNOVA is a multiview world model for driving scenarios that employs a dual-causal autoregressive framework.<n>It constructs an isotropic-temporal representation across views, frames, and scales based on relative Plcker-ray positional encoding.
  arXiv  Detail & Related papers  (2026-02-24T08:41:40Z)
• SymDrive: Realistic and Controllable Driving Simulator via Symmetric Auto-regressive Online Restoration [37.202523124756034]
  Current approaches often falter in large-angle novel view synthesis and suffer from geometric or lighting artifacts during asset manipulation.<n>We propose SymDrive, a unified diffusion-based framework capable of joint high-quality rendering and scene editing.<n>We demonstrate that SymDrive achieves photorealistic state-of-the-art performance in both novel-view enhancement and realistic 3D vehicle insertion.
  arXiv  Detail & Related papers  (2025-12-25T10:28:43Z)
• DGGT: Feedforward 4D Reconstruction of Dynamic Driving Scenes using Unposed Images [36.562825380568384]
  We introduce textbfDriving Gaussian Grounded Transformer (DGGT), a unified framework for pose-free dynamic scene reconstruction.<n>Our approach jointly predicts per-frame 3D Gaussian maps and camera parameters, disentangles dynamics with a lightweight dynamic head.<n>A diffusion-based rendering refinement further reduces motion/interpolation artifacts and improves novel-view quality under sparse inputs.
  arXiv  Detail & Related papers  (2025-12-02T18:29:18Z)
• Cross-Temporal 3D Gaussian Splatting for Sparse-View Guided Scene Update [17.581193784542357]
  Updating 3D scenes from sparse-view observations is crucial for various real-world applications.<n>We propose Cross-Temporal 3D Gaussian Splatting (Cross-Temporal 3DGS), a novel framework for efficiently reconstructing and updating 3D scenes.<n> Experimental results show significant improvements over baseline methods in reconstruction quality and data efficiency.
  arXiv  Detail & Related papers  (2025-11-29T16:00:24Z)
• UniSplat: Unified Spatio-Temporal Fusion via 3D Latent Scaffolds for Dynamic Driving Scene Reconstruction [26.278318116942526]
  We present UniSplat, a feed-forward framework that learns robust dynamic scene reconstruction through unified latent-temporal fusion.<n>Experiments on real-world datasets demonstrate that UniSplat achieves state-of-the-art synthesis in novel view, while providing robust and high-quality renderings for viewpoints outside the original camera coverage.
  arXiv  Detail & Related papers  (2025-11-06T17:49:39Z)
• DriveGen3D: Boosting Feed-Forward Driving Scene Generation with Efficient Video Diffusion [62.589889759543446]
  DriveGen3D is a novel framework for generating high-quality and highly controllable dynamic 3D driving scenes.<n>Our work bridges this methodological gap by integrating accelerated long-term video generation with large-scale dynamic scene reconstruction.
  arXiv  Detail & Related papers  (2025-10-17T03:00:08Z)
• 4D Driving Scene Generation With Stereo Forcing [62.47705572424127]
  Current generative models struggle to synthesize dynamic 4D driving scenes that simultaneously support temporal extrapolation and spatial novel view synthesis (NVS) without per-scene optimization.<n>We present PhiGenesis, a unified framework for 4D scene generation that extends video generation techniques with geometric and temporal consistency.
  arXiv  Detail & Related papers  (2025-09-24T15:37:17Z)
• Driv3R: Learning Dense 4D Reconstruction for Autonomous Driving [116.10577967146762]
  We propose Driv3R, a framework that directly regresses per-frame point maps from multi-view image sequences.<n>We employ a 4D flow predictor to identify moving objects within the scene to direct our network focus more on reconstructing these dynamic regions.<n>Driv3R outperforms previous frameworks in 4D dynamic scene reconstruction, achieving 15x faster inference speed.
  arXiv  Detail & Related papers  (2024-12-09T18:58:03Z)
• SCFusion: Real-time Incremental Scene Reconstruction with Semantic Completion [86.77318031029404]
  We propose a framework that performs scene reconstruction and semantic scene completion jointly in an incremental and real-time manner. Our framework relies on a novel neural architecture designed to process occupancy maps and leverages voxel states to accurately and efficiently fuse semantic completion with the 3D global model.
  arXiv  Detail & Related papers  (2020-10-26T15:31:52Z)

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.