AI Paper Atlas

Research map / 3D vision / Human pose estimation

Accurate and Efficient Object Pose Estimation via the Aggregation of Diffusion Features

Tianfu Wang, Guosheng Hu, H. G. Wang

IJCV 2024 · 3D vision › Human pose estimation · approach: Category-level object pose estimation · 21 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
replace ResNet template-pose features with aggregated Stable Diffusion features (CWA)Template-pose · Occluded-LINEMOD (unseen)accuracy (%): 77.9 -> 85.9Improved
use diffusion features (CWA) instead of Template-poseTemplate-pose · LINEMOD (unseen)accuracy (%): 94.4 -> 97.9Improved
replace vanilla aggregation with nonlinear aggregation (ablation)Ours (VA) · Occluded-LINEMOD (unseen)accuracy (%): 84.6 -> 85.5Improved
replace nonlinear aggregation with context-aware weight aggregation (ablation)Ours (NA) · Occluded-LINEMOD (unseen)accuracy (%): 85.5 -> 85.9Improved
replace CWA with confidence adaptive aggregation (early exit) (ablation)Ours (CWA) · LINEMODMACs / FPS: 929B -> 678B MACs; 9.2 -> 15.5 FPSImproved
replace CWA with confidence adaptive aggregationOurs (CWA) · LINEMOD (unseen)accuracy (%): 97.9 -> 97.7No clear effect
lower input resolution from 512 to 128 with CAAOurs (CAA) · T-LESSRecall VSD: 70.82 -> 69.52No clear effect
replace Stable Diffusion v1-5 with DINOv2 features (ablation)Ours (CWA) · Occluded-LINEMOD (unseen)accuracy (%): 85.9 -> 78.1Hurt
replace Stable Diffusion v1-5 with OpenCLIP features (ablation)Ours (CWA) · Occluded-LINEMOD (unseen)accuracy (%): 85.9 -> 81.1Hurt
replace SD-V1-5 with SD-V2-0 (ablation)Ours (CWA) · LINEMOD (unseen)accuracy (%): 97.9 -> 98.4No clear effect
raise confidence threshold from 0.65 to 0.7 (ablation)Ours (CAA) · Occluded-LINEMOD (unseen)accuracy (%): 83.0 -> 85.5Improved
raise confidence threshold from 0.7 to 0.75 (ablation)Ours (CAA) · Occluded-LINEMOD (unseen)accuracy / MACs: 85.5 -> 85.6; 719B -> 863B MACsNo clear effect

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