用一键扩散模型实时修复激光雷达视角偏移导致的场景失真
LidarPainter: One-Step Away From Any Lidar View To Novel Guidance
- 基于稀疏激光雷达和受损渲染图，一步完成新视角重建
- 速度比SOTA快7倍，显存仅需其1/5，支持高保真车道切换
- 可结合文本提示生成雾天、夜景等风格，扩展场景资产库
动态驾驶场景重建在数字孪生与自动驾驶仿真中至关重要。然而，当视角偏离输入轨迹时，背景与车辆模型会出现严重退化。现有方法存在一致性差、形变大、耗时长等局限。本文提出LidarPainter，一种一步式扩散模型，能从稀疏激光雷达条件和受损渲染结果中实时恢复一致的驾驶视图，实现高保真车道变换。大量实验表明，LidarPainter在速度、质量与资源效率上均优于当前最优方法：较StreetCrafter快7倍，仅需其1/5显存。该模型还支持通过文本提示（如“foggy”、“night”）进行风格化生成，丰富现有资产库。
原文摘要 · Abstract (English)
Dynamic driving scene reconstruction is of great importance in fields like digital twin system and autonomous driving simulation. However, unacceptable degradation occurs when the view deviates from the input trajectory, leading to corrupted background and vehicle models. To improve reconstruction quality on novel trajectory, existing methods are subject to various limitations including inconsistency, deformation, and time consumption. This paper proposes LidarPainter, a one-step diffusion model that recovers consistent driving views from sparse LiDAR condition and artifact-corrupted renderings in real-time, enabling high-fidelity lane shifts in driving scene reconstruction. Extensive experiments show that LidarPainter outperforms state-of-the-art methods in speed, quality and resource efficiency, specifically 7 x faster than StreetCrafter with only one fifth of GPU memory required. LidarPainter also supports stylized generation using text prompts such as "foggy" and "night", allowing for a diverse expansion of the existing asset library.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。