AI Paper Atlas

Research map / Point clouds / Segmentation and detection

DiffRefine: Diffusion-based Proposal Specific Point Cloud Densification for Cross-Domain Object Detection

Sangyun Shin, Yuhang He, Xinyu Hou, Samuel Hodgson, Andrew Markham, Niki Trigoni

ICCV 2025 · Point clouds › Segmentation and detection · approach: Multimodal and open-vocabulary 3D detection · 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
add spatial context feature f_gen (ablation)DiffRefine · Waymo->NuScenes (car)APBEV/AP3D: 1.58/1.06 gainImproved
add differentiable warping (gradient flow to refinement) (ablation)DiffRefine · Waymo->NuScenes (car)APBEV/AP3D: 0.59/0.43 gainImproved
add both differentiable warping and f_gen (ablation)DiffRefine · Waymo->NuScenes (car)AP3D: 23.73 -> 25.25Improved
use diffusion instead of voxel classification for generation (ablation)DiffRefine · Waymo->NuScenes (car)APBEV/AP3D: 20.44 -> 25.25 AP3D at 32^3Improved
shrink voxel grid from 32 to 8 for diffusion (ablation)DiffRefine · Waymo->NuScenes (car)AP3D: 25.25 -> 23.74Hurt
shrink voxel grid from 32 to 16 for classification (ablation)Voxel classification · Waymo->NuScenes (car)AP3D: 20.44 -> 21.87Mixed
increase denoising steps from 2 to 6 (ablation)DiffRefine · NuScenes->KITTIAP3D: 0.12, 0.08, 0.06, 0.03 per stepImproved
DiffRefine over ST3D baseline with SECOND-IoUSECOND-IoU · Waymo->KITTI (car)APBEV/AP3D: 7.03/9.61 gainImproved
DiffRefine over GroupExp-DA with SECOND-IoUSECOND-IoU · NuScenes->KITTI (car)APBEV/AP3D: 2.28/2.92 gainImproved
DiffRefine over best method on Pedestrian and CyclistSECOND-IoU · NuScenes->KITTIAPBEV/AP3D: 1.97/1.43 Pedestrian; 1.35/0.81 CyclistImproved

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