AI Paper Atlas

Research map / Image generation / Fast diffusion sampling

Adaptive Piecewise Distillation for Efficient LiDAR Data Generation

Ruibo Li, Xiaofeng Yang, Ze Yang, Jiacheng Wei, Chunyan Miao, Guosheng Lin

AAAI 2026 · Image generation › Fast diffusion sampling · approach: Distillation for few-step generation · 1 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
use adaptive piecewise distillation instead of timestep distillation on 2-RFR2Flow pixel-based, 4 steps · KITTI-360 unconditional (Range+Reflectance)FRD: 187.10 -> 165.31Improved
use adaptive piecewise distillation instead of the reflow operation (ablation)R2Flow pixel-based, 4 steps · KITTI-360 unconditional (Range+Reflectance)FRD: 221.87 -> 165.31Improved
use piecewise reflow instead of reflow at 4 steps (ablation)R2Flow pixel-based, 4 steps · KITTI-360 unconditional (Range+Reflectance)FRD: 221.87 -> 357.00Hurt
add adaptive timestep selection over uniform piecewise intervals (ablation)piecewise distillation · KITTI-360 unconditional (Range+Reflectance)FRD: 178.31 -> 165.31Improved
add adaptive timestep selection over uniform piecewise intervals (ablation)piecewise distillation · KITTI-360 unconditional (Range only)FRID: 145.7 -> 144.0Improved
add adaptive timestep selection over uniform piecewise intervals (ablation)piecewise distillation · KITTI-360 camera-to-LiDARFRID: 27.1 -> 27.0Improved
add adaptive timestep selection over uniform piecewise intervals (ablation)piecewise distillation · KITTI-360 camera-to-LiDARMMD: 3.40 -> 3.41No clear effect
use piecewise distillation (uniform) instead of reflow (ablation)4-step student · KITTI-360 unconditional (Range only)FRID: 164.9 -> 145.7Improved
distill 4-step student from teacher instead of sampling teacher with 4 steps (ablation)R2Flow 1-RF pixel-based · KITTI-360 unconditional (Range+Reflectance)FRD: 699.90 -> 165.31Improved
use 4-step LiDAR-Flow instead of 4-step LiDMlatent-based model · KITTI-360 unconditional (Range only)FRID: 305.5 -> 144.0Improved
use 4-step LiDAR-Flow instead of 4-step LiDMlatent-based model · SemanticKITTI semantic-map-to-LiDARFRID: 24.8 -> 13.9Improved
use 4-step LiDAR-Flow instead of 50-step LiDMlatent-based model · SemanticKITTI semantic-map-to-LiDARFRID: 12.3 -> 13.9Mixed

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