arXiv cs.AI· Andrea Ceron, Michael Schmidt, Alvaro Marcos-Ramiro, Sebastian Schmidt, Benjamin Busam·· 9 天前AI 评分25
CRISP：用扩散解码修复潜在 LiDAR 生成中的飞点
CRISP: Fixing Flying Pixels in Latent LiDAR Generation via Diffusion Decoding
AI 导读
CRISP 是一种像素空间扩散解码器，通过骨干无关的潜在适配器、基于 DiT 的去噪器与支撑掩码预测器，替换视频 VAE 和 LiDAR 原生解码器，同时保持编码器与潜在生成器不变。
正文 · 原文
Abstract:Latent LiDAR pipelines suffer from flying pixels: convolutional VAEs blur sharp radial depth discontinuities, yielding edge depths that back-project to points floating between surfaces. We identify this as a major, directly correctable decoder bottleneck and introduce CRISP: a pixel-space diffusion decoder with a backbone-agnostic latent adapter, DiT-based denoiser, and support mask predictor. CRISP replaces video-VAE and LiDAR-native decoders alike while keeping the encoder and latent generator fixed. Across KITTI-360, SemanticKITTI, and nuScenes, replacing only the decoder reduces FSVD/FPVD by 50.5% on average across frozen backbones; for generic video VAEs, the reductions reach 71%/74%. On the LiDAR-native LiDM backbone, FRID drops by 71%, with the largest gains at depth discontinuities. In a pretrained LiDM world model, the same zero-shot replacement improves FSVD by 15.5%, narrowing the sim-to-real gap.
| Comments: | Accepted at NeurIPS 2026 (poster). 41 pages, 10 figures, 18 tables. Project page: this https URL |
| Subjects: | Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI) |
| ACM classes: | I.2.10; I.4.8 |
| Cite as: | arXiv:2610.11376 [cs.CV] |
| (or arXiv:2610.11376v1 [cs.CV] for this version) | |
| https://doi.org/10.48550/arXiv.2610.11376 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Andrea Ceron [view email]
[v1]
Thu, 8 Oct 2026 07:07:55 UTC (5,944 KB)
来源：arXiv cs.AI · arxiv.org