AI Paper Atlas

Research map / Point clouds / Shape and surface completion

Structure-to-Intensity Diffusion for Adverse-Weather LiDAR Generation

Peiyang Ni, Longyu Yang, Lu Zhang, Kuniaki Saito, Yap-Peng Tan, Fumin Shen, Heng Tao Shen, Xiaofeng Zhu, Ping Hu

CVPR 2026 · Point clouds › Shape and surface completion · approach: Point cloud diffusion generation

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
replace WeatherGen MDP simulation with RPWS (ablation)WeatherGen (SMG backbone) · STF snow, no fine-tuningFPD: 271.12 -> 109.42Improved
replace SMG backbone with SiD (ablation)RPWS-trained generator · STF snow, no fine-tuningFPD: 109.42 -> 91.28Improved
add fine-tuning on real STF data (ablation)RPWS + SiD · STF snowFPD: 91.28 -> 32.38Improved
add reflectance degradation to RPWS (ablation)RPWS + SiD · STF snowFMD: 8.25 -> 3.67Improved
add geometry degradation to RPWS (ablation)RPWS + SiD · STF snowFPD: 475.11 -> 91.28Improved
condition intensity denoising on structure (S->I) versus independent (ablation)SiD · STF snowFMD: 4.92 -> 2.28Improved
reverse conditioning direction to I->S (ablation)SiD · STF snowFPD: 32.38 -> 66.20Hurt
use SiD instead of WeatherGen with only 10% real adverse dataSiD · STF snow, varying real data ratioFMDImproved
use SiD on clear-weather generationSiD · KITTI-360FMD: 1.86 -> 1.75 FMD; FPD 5.62 vs 4.81 for Text2LiDARMixed
use SiD (two-branch) instead of WeatherGen in parameters and computeSiD · efficiencyparameters / GFLOPs: 38.06M and 1.599 GFLOPs vs 32.59M and 1.398 GFLOPsNo clear effect

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 2 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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