AI Paper Atlas

Research map / 3D vision / Human pose estimation

IST-Net: Prior-Free Category-Level Pose Estimation with Implicit Space Transformation

Jianhui Liu, Yukang Chen, Xiaoqing Ye, Xiaojuan Qi

ICCV 2023 · 3D vision › Human pose estimation · approach: Category-level object pose estimation · 72 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 implicit space transformation supervision (IST) (ablation)IST-Net baseline · REAL2755°5cm: 42.9 -> 48.5Improved
add camera-space enhancer (ablation)IST-Net with IST · REAL2755°5cm: 48.5 -> 52.5Improved
add world-space enhancer (ablation)IST-Net with IST · REAL2753D75: 72.2 -> 75.9Improved
add position encoding term (ablation)IST-Net · REAL2755°5cm: 47.4 -> 53.4Improved
replace category-specific shape prior with random noise (ablation)DPDN · REAL2753D75: 76.0 -> 76.1No clear effect
replace category-specific shape prior with random noise (ablation)SGPA · REAL2753D75: 61.9 -> 60.3No clear effect
remove prior deformation moduleDPDN · REAL275accuracyImproved
use implicit instead of explicit space transformation (ablation)IST-Net · REAL275FPS: 22 -> 34Improved
use implicit instead of explicit space transformation (ablation)IST-Net · REAL2753D75: 75.1 -> 73.9Mixed
use MSE instead of L1 for the feature loss (ablation)IST-Net · REAL2755°5cm: 50.4 -> 53.4Improved
set feature loss weight lambda_f to 10 instead of 1 or 100 (ablation)IST-Net · REAL2755°5cm: 47.0 -> 53.4Improved
train IST-Net without fine-tuning on Wild6DIST-Net · Wild6D3D50: 68.2 -> 79.6Improved

Later papers that compared with this method

3 later accepted papers report IST-Net as a baseline in their results tables; 3 of them report a better number on most of the results they share with it.

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