OneFixer: High-Quality and Consistent One-Step Autoregressive 3DGS Refinement for Driving Scenes

arXiv:2609.32175 · cs.CV, cs.AI · Submitted 2026-09-26 · Read on arXiv

cs.CV, cs.AI

Submitted: 2026-09-26

Updated: 2026-09-26

Code: https://github.com/NVlabs/alpasim

Project page: https://onefixer-web.vercel.app

Terminology

• Consistency — 24× in this paper · explained in 3 episodes
• Distillation — 23× in this paper · explained in 2 episodes
• Fidelity — 20× in this paper · explained in 2 episodes
• Actor — 15× in this paper · explained in 3 episodes
• Flow Matching — 14× in this paper · explained in 7 episodes
• Temporal consistency — 12× in this paper · explained in 2 episodes
• Adaptation — 11× in this paper · explained in 1 episode
• Conference on Computer Vision and Pattern Recognition — 9× in this paper
• Diffusion Model — 9× in this paper · explained in 8 episodes
• Gaussian Splatting — 9× in this paper · explained in 4 episodes
• Diffusion Models — 7× in this paper · explained in 6 episodes
• Fine-Tuning — 7× in this paper · explained in 5 episodes
• World Model — 6× in this paper · explained in 7 episodes
• Robustness — 5× in this paper · explained in 5 episodes
• Ablation — 4× in this paper · explained in 1 episode
• Exposure Bias — 4× in this paper · explained in 2 episodes
• Generalization — 4× in this paper · explained in 13 episodes
• In European Conference on Computer Vision — 4× in this paper
• 3D Gaussian Splatting — 3× in this paper · explained in 2 episodes
• Adam — 3× in this paper · explained in 2 episodes
• Alignment — 3× in this paper · explained in 1 episode
• Benchmark — 3× in this paper · explained in 2 episodes
• Calibration — 3× in this paper · explained in 7 episodes
• Latent Space — 3× in this paper · explained in 7 episodes
• Transformer — 3× in this paper · explained in 2 episodes
• Aggregation — 2× in this paper · explained in 1 episode
• Distribution Matching — 2× in this paper · explained in 2 episodes
• Generative Model — 2× in this paper · explained in 2 episodes
• Generative Models — 2× in this paper · explained in 2 episodes
• International Conference on Computer Vision — 2× in this paper
• Reconstruction Error — 2× in this paper · explained in 2 episodes
• Redundancy — 2× in this paper · explained in 2 episodes
• Regularization — 2× in this paper · explained in 3 episodes
• 3D Gaussian Splatting (3DGS) — 1× in this paper · explained in 4 episodes
• Accuracy — 1× in this paper · explained in 1 episode
• Decode — 1× in this paper · explained in 2 episodes
• Generative AI — 1× in this paper · explained in 2 episodes
• I3D-based Frechet Video Distance — 1× in this paper
• Multimodal Dataset — 1× in this paper · explained in 2 episodes
• Optical Flow — 1× in this paper · explained in 2 episodes
• Reinforcement Learning — 1× in this paper · explained in 4 episodes
• Segmentation Masks — 1× in this paper · explained in 2 episodes
• Steering — 1× in this paper · explained in 2 episodes
• alpha — 1× in this paper · explained in 1 episode

Sources

• One-Forcing: Towards Stable One-Step Autoregressive Video Generation
• Towards Redundancy Reduction in Diffusion Models for Efficient Video Super-Resolution
• AutoAWG: Adverse Weather Generation with Adaptive Multi-Controls for Automotive Videos
• Rolling Sink: Bridging Limited-Horizon Training and Open-Ended Testing in Autoregressive Video Diffusion
• MTGS: Multi-Traversal Gaussian Splatting
• Fr'echet Video Motion Distance: A Metric for Evaluating Motion Consistency in Videos
• On-Policy Adversarial Flow Distillation for Autoregressive Video Generation
• Cosmos 3: Omnimodal World Models for Physical AI
• NVIDIA OmniDreams: Real-Time Generative World Model for Closed-Loop Autonomous Vehicle Simulation
• One-Step Image Translation with Text-to-Image Models
• Aligning Text-to-Image Diffusion Models with Reward Backpropagation
• ChopGrad: Pixel-Wise Losses for Latent Video Diffusion via Truncated Backpropagation
• Towards Accurate Generative Models of Video: A New Metric & Challenges
• Wan: Open and Advanced Large-Scale Video Generative Models
• Diffusion-DRF: Free, Rich, and Differentiable Reward for Video Diffusion Fine-Tuning
• GSFix3D: Diffusion-Guided Repair of Novel Views in Gaussian Splatting
• RealityBridge: Bridging Editable 3D Gaussian Splatting Driving Simulations and Real-World Videos
• Adaptive Video Distillation: Mitigating Oversaturation and Temporal Collapse in Few-Step Generation
• Degradation-Guided One-Step Image Super-Resolution with Diffusion Priors

Related papers

• Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
• AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
• Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
• MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
• TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
• A Survey on Efficient Vision-Language-Action Models