AI Paper Atlas

Research map / Image generation / Fast diffusion sampling

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

An Zhao, Shengyuan Zhang, Zejian Li, Ling Yang, Pei Chen, Jiale Wu, Haoran Xu, AnYang Wei, Perry Pengyun Gu, Lingyun Sun

AAAI 2026 · Image generation › Fast diffusion sampling · approach: Distillation for few-step generation · 4 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add preference-pair DPO term to score distillation (ablation)LiDiff student (8 NFE) · SemanticKITTI (Refined)Chamfer Distance: 0.419 -> 0.354Improved
plain score distillation vs teacher (ablation)LiDiff · SemanticKITTI (Refined)Chamfer Distance: 0.375 -> 0.419Hurt
distill 50-step LiDiff into 8-step student with preference alignmentLiDiff · SemanticKITTI (Refined)time (s): 17.87 -> 3.38Improved
reduce sampling steps from 8 to 4 (ablation)Distillation-DPO · SemanticKITTI (Refined)Chamfer Distance: 0.354 -> 0.369Hurt
reduce sampling to 1 step (ablation)Distillation-DPO · SemanticKITTI (Refined)Chamfer Distance: 0.354 -> 0.601Hurt
increase initial noise scale lambda from 1.1 to 1.5 (ablation)Distillation-DPO pair generation · SemanticKITTI (Refined)Chamfer Distance: 0.354 -> 0.409Hurt
decrease lambda from 1.1 to 1.05 (ablation)Distillation-DPO pair generation · SemanticKITTI (Refined)Chamfer Distance: 0.354 -> 0.358Hurt
use a stronger teacher (LiDiff refined with Diffusion-DPO) (ablation)Distillation-DPO · SemanticKITTI (Refined)Chamfer Distance: 0.354 -> 0.343Improved
choose preference pairs by JSD instead of CD (ablation)Distillation-DPO · SemanticKITTI (Refined)Chamfer Distance: 0.354 -> 0.382Hurt
use two auxiliary diffusion models (win and lose) instead of one (ablation)Distillation-DPO · SemanticKITTI (Refined)Chamfer Distance: 0.372 -> 0.354Improved
Distillation-DPO vs refined LiDiff at 8 NFEDistillation-DPO · SemanticKITTI (Refined)EMD: 23.16 -> 23.66 (vs LiDiff 50 NFE)Hurt

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy