PRG-Fusion: Orchestrating Generative Priors with Reconstruction Evidence for Driving View Synthesis

• URL: http://arxiv.org/abs/2609.06948v1
• Date: Mon, 07 Sep 2026 02:34:51 GMT
• Title: PRG-Fusion: Orchestrating Generative Priors with Reconstruction Evidence for Driving View Synthesis
• Abstract summary: 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.
• Score: 16.51293833344591
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Synthesizing photorealistic driving videos along specified trajectories is essential for scalable closed-loop simulation. Reconstruction-based methods leverage neural rendering to synthesize geometrically consistent views, but often exhibit diverse artifacts and missing content when the viewpoint deviates from the training trajectory. In contrast, generative models can synthesize realistic views along arbitrary trajectories from vehicle sensor data, yet often struggle to maintain temporal and geometric consistency across frames. To combine the strengths of both, we propose PRG-Fusion, a framework for driving view synthesis that uses reconstruction evidence to orchestrate generative priors across regions. Specifically, we extract region-wise degradation evidence from reconstructed driving scenes and convert it into Preserve, Repair, and Generate (PRG) labels. At inference, these labels serve as a unified routing policy for region-aware spatiotemporal synthesis, orchestrating 3DGS appearance preservation, LiDAR-guided structural correction, and video-prior-driven content completion across Preserve, Repair, and Generate regions, respectively. We then follow a two-stage training paradigm, first establish geometric control from sparse LiDAR projections and subsequently learning appearance control from dense 3DGS renderings. Extensive experiments on Waymo demonstrate that PRG-Fusion achieves state-of-the-art overall performance in novel trajectory video synthesis, with superior visual quality and geometric fidelity while maintaining competitive view consistency under large trajectory shifts.

Related papers

• GaussVid: Sparse-View Gaussian Splatting with 3D-Aware Video Diffusion Priors [14.045684695919116]
  3DGS has achieved remarkable success in synthesis; however, reconstructions under sparse views often exhibit noticeable artifacts.<n>We propose a novel 3D-aware video restoration framework designed to enhance the quality of sparse 3DGS reconstruction.<n>Our approach attains the best pixel- and structure-level fidelity (PSNR/SSIM) and improves multi-view consistency.
  arXiv  Detail & Related papers  (2026-08-22T08:47:29Z)
• 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)
• FlowObject: Flow Steering for Bridging Generative Priors and Reconstruction Fidelity [34.142288038459704]
  FlowObject is a framework that reformulates sparse-view 3D reconstruction as a training-free, guided inverse problem.<n>Our method significantly outperforms state-of-the-art generative models and optimization-based frameworks in both geometric completeness and view-dependent appearance fidelity.
  arXiv  Detail & Related papers  (2026-06-17T12:42:09Z)
• VidSplat: Gaussian Splatting Reconstruction with Geometry-Guided Video Diffusion Priors [79.88300861391114]
  VidSplat is a training-free generative reconstruction framework.<n>We tackle two key challenges that enable the effective integration of generation and reconstruction.<n>Experiments on widely used benchmarks demonstrate our superior performance in sparse-view scene reconstruction.
  arXiv  Detail & Related papers  (2026-05-12T02:20:31Z)
• ViPS: Video-informed Pose Spaces for Auto-Rigged Meshes [55.32681167870698]
  Video-informed Pose Spaces (ViPS) is a feed-forward framework that discovers the latent distribution of valid articulations for auto-rigged meshes.<n>ViPS transfers generative video priors into a universal distribution over a given rig parameterization.<n>Our evaluations show that ViPS matches the performance of state-of-the-art methods trained on synthetic artist-created 4D data in both plausibility and diversity.
  arXiv  Detail & Related papers  (2026-04-19T21:21:11Z)
• FreeGen: Feed-Forward Reconstruction-Generation Co-Training for Free-Viewpoint Driving Scene Synthesis [24.76850299847588]
  FreeGen is a feed-forward reconstruction-generation co-training framework for free-viewpoint driving scene.<n>We show that FreeGen achieves state-of-the-art performance for free-viewpoint driving scene synthesis.
  arXiv  Detail & Related papers  (2025-12-04T14:14:21Z)
• HBSplat: Robust Sparse-View Gaussian Reconstruction with Hybrid-Loss Guided Depth and Bidirectional Warping [11.035994094874141]
  HBSplat is a framework that seamlessly integrates robust structural cues, virtual view constraints, and occluded region completion.<n> HBSplat sets a new state-of-the-art, achieving up to 21.13 dB PSNR and 0.189 LPIPS, while maintaining real-time inference.
  arXiv  Detail & Related papers  (2025-09-29T15:03:31Z)
• 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)
• 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)
• Structural Energy-Guided Sampling for View-Consistent Text-to-3D [18.973527029488746]
  Text-to-3D generation often suffers from the Janus problem, where objects collapse into duplicated or distorted geometry from other angles.<n>We propose Structural Energy-Guided Sampling (SEGS), a training-free, plug-and-play framework that enforces multi-view consistency entirely at sampling time.
  arXiv  Detail & Related papers  (2025-08-23T06:26:04Z)
• HumanGenesis: Agent-Based Geometric and Generative Modeling for Synthetic Human Dynamics [60.737929335600015]
  We present textbfHumanGenesis, a framework that integrates geometric and generative modeling through four collaborative agents.<n>HumanGenesis achieves state-of-the-art performance on tasks including text-guided synthesis, video reenactment, and novel-pose generalization.
  arXiv  Detail & Related papers  (2025-08-13T14:50:19Z)
• Driving View Synthesis on Free-form Trajectories with Generative Prior [39.24591650300784]
  DriveX is a novel free-form driving view synthesis framework.<n>It distills generative prior into the 3D Gaussian model during its optimization.<n>It achieves high-quality view synthesis beyond recorded trajectories in real time.
  arXiv  Detail & Related papers  (2024-12-02T17:07:53Z)

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.