paper-with-me

Papers

3D AffordanceNet: A Benchmark for Visual Object Affordance Understanding

2021-03-30 · CVPR 2021 1 · Shengheng Deng, Xun Xu, Chaozheng Wu, Ke Chen, Kui Jia

The ability to understand the ways to interact with objects from visual cues, a.k.a. visual affordance, is essential to vision-guided robotic research. This involves categorizing, segmenting and reasoning of visual affordance. Relevant studies in 2D and 2.5D image domains have been made previously, however, a truly functional understanding of object affordance requires learning and prediction in the 3D physical domain, which is still absent in the community. In this work, we present a 3D AffordanceNet dataset, a benchmark of 23k shapes from 23 semantic object categories, annotated with 18 visual affordance categories. Based on this dataset, we provide three benchmarking tasks for evaluating visual affordance understanding, including full-shape, partial-view and rotation-invariant affordance estimations. Three state-of-the-art point cloud deep learning networks are evaluated on all tasks. In addition we also investigate a semi-supervised learning setup to explore the possibility to benefit from unlabeled data. Comprehensive results on our contributed dataset show the promise of visual affordance understanding as a valuable yet challenging benchmark.

📄 PDF Abstract BibTeX arXiv:2103.16397

Code (1)

Gorilla-Lab-SCUT/AffordanceNet 공식 구현 pytorch

Tasks

Affordance DetectionBenchmarkingObject

Similar Papers 제목 키워드 기반

AffordanceNet: An End-to-End Deep Learning Approach for Object Affordance Detection

2017-09-21 · Thanh-Toan Do, Anh Nguyen, Ian Reid

We propose AffordanceNet, a new deep learning approach to simultaneously detect multiple objects and their affordances from RGB images. Our AffordanceNet has two branches: an object detection branch to localize and class…

Affordance DetectionObjectobject-detectionObject Detection

PanoAffordanceNet: Towards Holistic Affordance Grounding in 360° Indoor Environments

2026-03-10 · Guoliang Zhu, Wanjun Jia, Caoyang Shao, Yuheng Zhang 외 arxiv

Global perception is essential for embodied agents in 360° spaces, yet current affordance grounding remains largely object-centric and restricted to perspective views. To bridge this gap, we introduce a novel task: Holis…

PAVLM: Advancing Point Cloud based Affordance Understanding Via Vision-Language Model

2024-10-15 · Shang-Ching Liu, Van Nhiem Tran, Wenkai Chen, Wei-Lun Cheng 외

Affordance understanding, the task of identifying actionable regions on 3D objects, plays a vital role in allowing robotic systems to engage with and operate within the physical world. Although Visual Language Models (VL…

Language ModelingLanguage Modelling

RAGNet: Large-scale Reasoning-based Affordance Segmentation Benchmark towards General Grasping

2025-07-31 · Dongming Wu, Yanping Fu, Saike Huang, Yingfei Liu 외 arxiv

General robotic grasping systems require accurate object affordance perception in diverse open-world scenarios following human instructions. However, current studies suffer from the problem of lacking reasoning-based lar…

Robot ManipulationRobotic Grasping

Interpretable Affordance Detection on 3D Point Clouds with Probabilistic Prototypes

2025-04-25 · Maximilian Xiling Li, Korbinian Rudolf, Nils Blank, Rudolf Lioutikov

Robotic agents need to understand how to interact with objects in their environment, both autonomously and during human-robot interactions. Affordance detection on 3D point clouds, which identifies object regions that al…

Affordance DetectionDecision Making