Affordance Detection
13 papers with code • 4 benchmarks • 3 datasets
Affordance detection refers to identifying the potential action possibilities of objects in an image, which is an important ability for robot perception and manipulation.
Image source: Object-Based Affordances Detection with Convolutional Neural Networks and Dense Conditional Random Fields
Unlike other visual or physical properties that mainly describe the object alone, affordances indicate functional interactions of object parts with humans.
Benchmarks
These leaderboards are used to track progress in Affordance Detection
| Trend | Dataset | Best Model | Paper | Code | Compare |
|---|---|---|---|---|---|
|
|||||
|
|||||
|
|||||
|
Libraries
Use these libraries to find Affordance Detection models and implementations
3D AffordanceNet
PADv2
Visual Affordance Learning
Most implemented papers
Phrase-Based Affordance Detection via Cyclic Bilateral Interaction
lhc1224/OSAD_Net
•
•
In this paper, we explore to perceive affordance from a vision-language perspective and consider the challenging phrase-based affordance detection problem, i. e., given a set of phrases describing the action purposes, all the object regions in a scene with the same affordance should be detected.
AffordanceNet: An End-to-End Deep Learning Approach for Object Affordance Detection
We propose AffordanceNet, a new deep learning approach to simultaneously detect multiple objects and their affordances from RGB images.
Affordance Transfer Learning for Human-Object Interaction Detection
The proposed method can thus be used to 1) improve the performance of HOI detection, especially for the HOIs with unseen objects; and 2) infer the affordances of novel objects.
One-Shot Affordance Detection
lhc1224/OSAD_Net
•
•
To empower robots with this ability in unseen scenarios, we consider the challenging one-shot affordance detection problem in this paper, i. e., given a support image that depicts the action purpose, all objects in a scene with the common affordance should be detected.
Weakly Supervised Affordance Detection
Localizing functional regions of objects or affordances is an important aspect of scene understanding and relevant for many robotics applications.
What can I do here? Leveraging Deep 3D saliency and geometry for fast and scalable multiple affordance detection
eduard626/interaction-tensor-affordances
•
•
This paper develops and evaluates a novel method that allows for the detection of affordances in a scalable and multiple-instance manner on visually recovered pointclouds.
Recognizing Object Affordances to Support Scene Reasoning for Manipulation Tasks
Unfortunately, the top performing affordance recognition methods use object category priors to boost the accuracy of affordance detection and segmentation.
3D AffordanceNet: A Benchmark for Visual Object Affordance Understanding
Gorilla-Lab-SCUT/AffordanceNet
•
•
CVPR 2021
The ability to understand the ways to interact with objects from visual cues, a. k. a.
One-Shot Object Affordance Detection in the Wild
lhc1224/OSAD_Net
•
•
To empower robots with this ability in unseen scenarios, we first study the challenging one-shot affordance detection problem in this paper, i. e., given a support image that depicts the action purpose, all objects in a scene with the common affordance should be detected.
Detecting Object States vs Detecting Objects: A New Dataset and a Quantitative Experimental Study
This study enables the setup of a baseline on the performance of SD, as well as its relative performance in comparison to OD, in a variety of scenarios.
