AI Paper Atlas

Research map / 3D vision / 3D generation

Articulated Object Reconstruction from Rest-State Observation

Daeun Lee, Jaeah Lee, Woosung Kim, Haebeom Jung, Jaesik Park

ECCV 2026 · 3D vision › 3D generation · approach: Monocular 3D object reconstruction · 0 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 co-refinement loop between GPT-5.2 and SAM3 (ablation)GPT-5.2 + SAM3 · ACDhierarchy tree accuracy: 62.3 -> 72.5Improved
add co-refinement loop between Qwen3-VL and SAM3 (ablation)Qwen3-VL + SAM3 · ACDhierarchy tree accuracy: 52.2 -> 72.5Improved
add co-refinement loop between Qwen3-VL and SAM3 (ablation)Qwen3-VL + SAM3 · ACDper-part count accuracy: 47.8 -> 63.8Improved
add co-refinement loop between GPT-5.2 and SAM3 (ablation)GPT-5.2 + SAM3 · ACDper-part count accuracy: 59.4 -> 59.4No clear effect
add co-refinement to Singapo (ablation)Singapo · ACD-ABOtype accuracy: 41.47 -> 67.94Improved
add co-refinement to Singapo (ablation)Singapo · ACD-HSSDtype accuracy: 59.42 -> 61.21Improved
use 2DGS instead of 3DGS for mesh backend (ablation)proposed pipeline · ACDsegmentation IoU: 0.30 -> 0.97Improved
use 2DGS instead of 3DGS for mesh backend (ablation)proposed pipeline · ACDaxis direction error: 1.69 -> 3.67Hurt
add mask overlay to video generation (ablation)Wan2.2 + VBVR LoRA · ACD-HSSDaccurate articulation rate: 69.2% -> 80.8%Improved
add mask overlay to video generation (ablation)Wan2.2 + VBVR LoRA · ACD-HSSDhallucination rate: 23.1% -> 11.5%Improved
raise max refinement rounds from 2 to 20 (ablation)co-refinement · ACDconvergence rate: 84.1% -> 92.8%Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 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