← Search

AnYang Wei

2 accepted papers

2026

Diffusion Distillation with Direct Preference Optimization for Efficient 3D LiDAR Scene Completion

AAAI 2026technical

The slow sampling speed of diffusion models hinders their application in 3D LiDAR scene completion. To address this, we propose Distillation-DPO, a novel framework that accelerates sampling through score distillation while simultaneously enhancing generation quality via preference alignment. Disti

Cited by 0SourcePDFScholar
2025

Distilling Diffusion Models to Efficient 3D LiDAR Scene Completion

ICCV 2025poster

Diffusion models have been applied to 3D LiDAR scene completion due to their strong training stability and high completion quality. However, the slow sampling speed limits the practical application of diffusion-based scene completion models since autonomous vehicles require an efficient perception o…