A large scale multi-view RGBD visual affordance learning dataset

TL;DR

This paper introduces the first and largest multi-view RGBD dataset for visual affordance learning, enabling improved recognition, detection, and segmentation of affordances for intelligent interaction with objects.

Contribution

It provides a large-scale, annotated RGBD dataset for visual affordance understanding, and benchmarks multiple deep learning models on this new dataset.

Findings

The dataset contains 47,210 images across 37 object categories.

State-of-the-art models show promising results but also highlight the dataset's challenging nature.

The dataset facilitates future research in robust affordance learning algorithms.

Abstract

The physical and textural attributes of objects have been widely studied for recognition, detection and segmentation tasks in computer vision.~A number of datasets, such as large scale ImageNet, have been proposed for feature learning using data hungry deep neural networks and for hand-crafted feature extraction. To intelligently interact with objects, robots and intelligent machines need the ability to infer beyond the traditional physical/textural attributes, and understand/learn visual cues, called visual affordances, for affordance recognition, detection and segmentation. To date there is no publicly available large dataset for visual affordance understanding and learning. In this paper, we introduce a large scale multi-view RGBD visual affordance learning dataset, a benchmark of 47210 RGBD images from 37 object categories, annotated with 15 visual affordance categories. To the best of our knowledge, this is the first ever and the largest multi-view RGBD visual affordance learning dataset. We benchmark the proposed dataset for affordance segmentation and recognition tasks using popular Vision Transformer and Convolutional Neural Networks. Several state-of-the-art deep learning networks are evaluated each for affordance recognition and segmentation tasks. Our experimental results showcase the challenging nature of the dataset and present definite prospects for new and robust affordance learning algorithms. The dataset is publicly available at https://sites.google.com/view/afaqshah/dataset.