# CRISP: Fixing Flying Pixels in Latent LiDAR Generation via Diffusion Decoding

arXiv: https://arxiv.org/abs/2610.11376 · HTML: https://mlsanity.com/paper/2610.11376/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 23 of its 71 references that are in the map.
- First posted on arXiv 8 Oct 2026.

## Builds on (most cited first, 23 of 23)

- [Score-Based Generative Modeling through Stochastic Differential Equations](https://mlsanity.com/paper/2011.13456/) (2020)
- [Auto-Encoding Variational Bayes](https://mlsanity.com/paper/1312.6114/) (2013)
- [Gaussian Error Linear Units (GELUs)](https://mlsanity.com/paper/1606.08415/) (2016)
- [Wan: Open and Advanced Large-Scale Video Generative Models](https://mlsanity.com/paper/2503.20314/) (2025)
- [Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasets](https://mlsanity.com/paper/2311.15127/) (2023)
- [Progressive Distillation for Fast Sampling of Diffusion Models](https://mlsanity.com/paper/2202.00512/) (2022)
- [3D and 4D World Modeling: A Survey](https://mlsanity.com/paper/2509.07996/) (2025)
- [A Survey of World Models for Autonomous Driving](https://mlsanity.com/paper/2501.11260/) (2025)
- [Pixel-Perfect Depth with Semantics-Prompted Diffusion Transformers](https://mlsanity.com/paper/2510.07316/) (2025)
- [WorldLens: Full-Spectrum Evaluations of Driving World Models in Real World](https://mlsanity.com/paper/2512.10958/) (2025)
- [Epsilon-VAE: Denoising as Visual Decoding](https://mlsanity.com/paper/2410.04081/) (2024)
- [LOGen: Toward Lidar Object Generation by Point Diffusion](https://mlsanity.com/paper/2412.07385/) (2024)
- [UniDriveDreamer: A Single-Stage Multimodal World Model for Autonomous Driving](https://mlsanity.com/paper/2602.02002/) (2026)
- [U4D: Uncertainty-Aware 4D World Modeling from LiDAR Sequences](https://mlsanity.com/paper/2512.02982/) (2025)
- [PiD: Fast and High-Resolution Latent Decoding with Pixel Diffusion](https://mlsanity.com/paper/2605.23902/) (2026)
- [Taming Transformers for Realistic Lidar Point Cloud Generation](https://mlsanity.com/paper/2404.05505/) (2024)
- [Forging Spatial Intelligence: A Roadmap of Multi-Modal Data Pre-Training for Autonomous Systems](https://mlsanity.com/paper/2512.24385/) (2025)
- [L3DR: 3D-aware LiDAR Diffusion and Rectification](https://mlsanity.com/paper/2602.19064/) (2026)
- [Latent World Models for Automated Driving: A Unified Taxonomy, Evaluation Framework, and Open Challenges](https://mlsanity.com/paper/2603.09086/) (2026)
- [Adverse Weather Conditions Augmentation of LiDAR Scenes with Latent Diffusion Models](https://mlsanity.com/paper/2501.01761/) (2025)
- [R3DPA: Leveraging 3D Representation Alignment and RGB Pretrained Priors for LiDAR Scene Generation](https://mlsanity.com/paper/2601.07692/) (2026)
- [Physically Based Neural LiDAR Resimulation](https://mlsanity.com/paper/2507.12489/) (2025)
- [Range-Edit: Semantic Mask Guided Outdoor LiDAR Scene Editing](https://mlsanity.com/paper/2511.17269/) (2025)

## Abstract (arXiv)

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.