AI Paper Atlas

Research map / 3D vision / Human pose estimation

BoxDreamer: Dreaming Box Corners for Generalizable Object Pose Estimation

Yuanhong Yu, Xingyi He, Chen Zhao, Junhao Yu, Jiaqi Yang, Ruizhen Hu, Yujun Shen, Xing Zhu, Xiaowei Zhou, Sida Peng

ICCV 2025 · 3D vision › Human pose estimation · approach: Category-level object pose estimation · 3 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 real-data (OnePose) training (ablation)BoxDreamer · LINEMOD (5 refs)ADD(s)-0.1d: 40.6 -> 51.3Improved
add real-data (OnePose) training (ablation)BoxDreamer · LINEMOD (5 refs)Proj2D@5px: 25.4 -> 43.8Improved
use DUSt3R box instead of ground-truth box (ablation)BoxDreamer · LINEMOD (5 refs)ADD(s)-0.1d: 49.3 -> 51.3No clear effect
use DUSt3R box instead of ground-truth box (ablation)BoxDreamer · LINEMOD (5 refs)Proj2D@5px: 51.8 -> 43.8Hurt
use OnePose++ box instead of DUSt3R box (ablation)BoxDreamer · LINEMOD (5 refs)Proj2D@5px: 43.8 -> 52.7Improved
increase references from 5 to 32 (ablation)BoxDreamer · LINEMOD subsetADD(s)-0.1d: 53.1 -> 69.2Improved
BoxDreamer vs GS-Pose at 5 referencesBoxDreamer · LINEMOD subset (5 refs)ADD(s)-0.1d: 25.6 -> 53.1Improved
BoxDreamer vs GS-Pose at 32 referencesBoxDreamer · LINEMOD subset (32 refs)ADD(s)-0.1d: 74.5 -> 69.2Hurt
BoxDreamer vs OnePose++ with 10 referencesBoxDreamer · OnePose-LowTextureADD-0.1d: 58.0 -> 86.6Improved
use denser 200-reference database for baselinesGen6D · YCB-Video most-overlapping databaseADD: 14.6 -> 22.9No clear effect
use occlusion-minimizing reference database instead of most-overlappingBoxDreamer · YCB-VideoADD: 35.4 -> 37.8Improved

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