AI Paper Atlas

Research map / 3D vision / 3D generation

Diffusion Models are Open-World Affordance Learners: Leveraging Generative Priors for 3D Affordance Learning

Hanqing Wang, Zhenhao Zhang, Kaiyang Ji, Mingyu Liu, Wenti Yin, yuchao chen, Zhirui Liu, Xiangyu Zeng, Tianxiang Gui, Hangxing Zhang, Jiahao Yuan, Zhiqing Cui and 3 more

ECCV 2026 · 3D vision › 3D generation · approach: Score distillation for text-to-3D · 9 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
use diffusion U-Net features instead of ResNet/CLIP/DINOv2 as affordance extractor (ablation)DAG · PIAD1 SeenmIoU: 22.3 (DINOv2) -> 24.84Improved
add Affordance Block (ablation)DAG · PIAD1 SeenmIoU: 10.02 -> 18.56Improved
add [CLS] token (ablation)DAG · PIAD1 SeenmIoU: 18.56 -> 24.84Improved
add Affordance Block (ablation)DAG · PIAD1 UnseenmIoU: 8.45 -> 9.02Improved
use implicit ASE caption instead of empty, BLIP or verb text (ablation)DAG · PIAD1 SeenmIoU: 20.2 (Verb) -> 24.84Improved
use diffusion timestep 0 instead of 50 or 100 (ablation)DAG · PIAD1 SeenmIoU: 21.93 (t=100) -> 24.85 (t=0)Improved
use DAG instead of GREAT on unseen objectsDAG · PIAD2 Unseen ObjmIoU: 20.16 -> 28.93Improved
train DAG with 5 shots (2% data) vs full-data PFU baselineDAG · PIAD1 SeenmIoU: 12.31 (PFU all data) -> 15.74Improved
reduce training data from all to 1 shotDAG · PIAD1 SeenmIoU: 24.84 -> 12.98Hurt

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