AI Paper Atlas

Research map / 3D vision / Human pose estimation

High-Resolution Open-Vocabulary Object 6D Pose Estimation

Jaime Corsetti, Davide Boscaini, Francesco Giuliari, Changjae Oh, Andrea Cavallaro, Fabio Poiesi

TPAMI 2025 · 3D vision › Human pose estimation · approach: Instance-level 6D object pose · 12 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 crop and updated loss hyperparameters together (ablation)Horyon · Average of 4 datasetsAR: 20.9 -> 33.4Improved
add crop (original loss hyperparameters) (ablation)Horyon · Average of 4 datasetsAR: 20.9 -> 25.3Improved
update loss hyperparameters without crop (ablation)Horyon · Average of 4 datasetsAR: 20.8 -> 17.8Hurt
add cross-attention fusion of visual and text (ablation)Horyon · Average of 4 datasetsAR: 29.4 -> 33.4Improved
use cross-attention fusion instead of Oryon similarity aggregation (ablation)Horyon · Average of 4 datasetsAR: 30.6 -> 33.4Improved
use three DINO guidance maps instead of two (ablation)Horyon · Average of 4 datasetsAR: 31.4 -> 33.4Improved
add skip connections from DINO to decoder (ablation)Horyon · Average of 4 datasetsAR: 30.6 -> 33.4Improved
use DINO instead of Swin-B guidance (ablation)Horyon · Average of 4 datasetsAR: 31.3 -> 33.4Improved
use GDino VLM with token-wise features instead of CLIP (ablation)Horyon · Average of 4 datasetsAR: 23.1 -> 31.3Improved
use GDino VLM instead of ALIGN (ablation)Horyon · Average of 4 datasetsAR: 23.4 -> 31.3Improved
include object name in prompt (ablation)Horyon · Average of 4 datasetsAR: 18.7 -> 33.4Improved
use correct description instead of misleading one (ablation)Horyon · Average of 4 datasetsAR: 22.5 -> 33.4Improved

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