[Submitted on 8 Oct 2026 (v1), last revised 2 Nov 2026 (this version, v3)]
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. Code and checkpoints will be released at this https URL.
Submission history
From: Andrea Ceron [view email]
[v1] Thu, 8 Oct 2026 07:07:55 UTC (5,944 KB)
[v2] Tue, 20 Oct 2026 08:29:51 UTC (5,944 KB)
[v3] Mon, 2 Nov 2026 13:20:40 UTC (5,944 KB)
