AI Paper Atlas

Research map / 3D vision / 3D generation

Task-Aware 3D Affordance Segmentation via 2D Guidance and Geometric Refinement

Lian He, Meng Liu, Qilang Ye, Yu Zhou, Xiang Deng, Gangyi Ding

AAAI 2026 · 3D vision › 3D generation · approach: Open-vocabulary 3D scene understanding · 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 affordance-weighted frame selection (ablation)TASA 2D detection · SceneFun3D Split0mIoU: 4.4 -> 11.3Improved
add double-check point validation (ablation)TASA 2D detection · SceneFun3D Split0mAP: 3.9 -> 13.1Improved
use both frame selection and double check (ablation)TASA 2D detection · SceneFun3D Split0mAP: 3.9 -> 23.2Improved
add color and text inputs to the 3D refinement module (ablation)TASA 3D refinement · SceneFun3D Split0mAP: 23.2 -> lower (see Table 4)Hurt
select K=10 frames instead of K=20 (ablation)TASA frame selection · SceneFun3DmIoUNo clear effect
use only one frame for selection (ablation)TASA frame selection · SceneFun3DmIoUHurt
replace Fun3DU's 2D lifting with TASAFun3DU · SceneFun3DmAP: 7.6 -> 23.2Improved
replace Fun3DU with TASAFun3DU · SceneFun3DAP25: 33.3 -> 28.6Hurt
replace Fun3DU with TASAFun3DU · SceneFun3Dinference time (s/sample): 130.26 -> 37.61Improved

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