AI Paper Atlas

Research map / 3D vision / Human pose estimation

PACE: Pose Annotations in Cluttered Environments

Yang You, kai xiong, Zhening Yang, Zhengxiang Huang, Junwei Zhou, Ruoxi Shi, Zhou FANG, Adam Harley, Leonidas Guibas, Cewu Lu

ECCV 2024 · 3D vision › Human pose estimation · approach: Category-level object pose estimation

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
evaluate SOTA category-level methods on PACE instead of NOCS-REAL275HS-Pose, DualPoseNet, SARNet · bottle, bowl, can, mugAP@15deg5cm: 99.8 -> 0.4 (HS-Pose bottle)Hurt
use classical PPF instead of deep learning methods for instance-level pose estimationPACE instance-level benchmark · PACEAR: 9.0 -> 52.2Improved
train on simulated data instead of real data (single instance/category) (ablation)GDRNPP · PACE instance-levelAR (%): 88.2 -> 78.1Hurt
train on simulated data instead of real data (single category) (ablation)HS-Pose · PACE category-levelmean AP@0:60deg,0:15cm: 81.2 -> 1.1Hurt
scale training from a single instance to all instances (ablation)GDRNPP · PACE instance-levelAR (%): 88.2 -> 9.7Hurt
scale training from a single category to all categories (ablation)CPPF++ · PACE category-levelmean AP@0:60deg,0:15cm: 83.4 -> 13.7Hurt
apply rigid-object-focused category-level methods to articulated objectscategory-level methods on PACE · PACE articulated objectsAPHurt
use depth-based model ICG instead of RGB-only RBOT for model-based trackingmodel-based tracking · PACE rigidADD(-S) AUC: 7.4 -> 38.1Improved

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