AI Paper Atlas

Research map / Point clouds / Registration and matching

SE(3) Diffusion Model-based Point Cloud Registration for Robust 6D Object Pose Estimation

Haobo Jiang, Mathieu Salzmann, Zheng Dang, Jin Xie, Jian Yang

NeurIPS 2023 · Point clouds › Registration and matching · approach: Non-rigid point set registration · 10 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
wrap DCP in SE(3) diffusion framework (Diff-DCP)DCP · LINEMOD5deg mAP: 0.06 -> 0.22Improved
wrap DCP in SE(3) diffusion framework (Diff-DCP)DCP · TUD-L1cm mAP: 0.04 -> 0.73Improved
wrap RPMNet in SE(3) diffusion framework (Diff-RPMNet)RPMNet · TUD-L5deg mAP: 0.73 -> 0.90Improved
wrap RPMNet in SE(3) diffusion framework (Diff-RPMNet)RPMNet · Occluded-LINEMOD5deg mAP: 0.03 -> 0.12Improved
add diffusion-generated pose augmentation (DiffAug) to training (ablation)DCP · LINEMOD1cm mAP: 0.11 -> 0.52Improved
add reverse denoising process on top of DiffAug (ablation)DCP+DiffAug · LINEMOD1cm mAP: 0.52 -> 0.65Improved
use cosine instead of linear noise schedule (ablation)Diff-DCP · LINEMOD1cm mAP: 0.56 -> 0.65Improved
use cosine instead of linear noise schedule (ablation)Diff-DCP · TUD-L1cm mAP: 0.93 -> 0.73Hurt
use deterministic instead of random inference (ablation)Diff-DCP · LINEMOD1cm mAP: 0.62 -> 0.65Improved
increase diffusion steps from 50 to 200 (ablation)Diff-DCP · LINEMOD1cm mAP: 0.54 -> 0.65Improved
increase diffusion steps from 100 to 200 (ablation)Diff-DCP · TUD-L1cm mAP: 0.87 -> 0.73Hurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 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