• Home
  • Search
  • A Multi-scale CNN for Affordance Segmentation in RGB Images
  • Cite Icon171
  • https://doi.org/10.1007/978-3-319-46493-0_12Copy DOI Icon

A Multi-scale CNN for Affordance Segmentation in RGB Images

  • Jan 1, 2016
  • Anirban Roy +1 more
Show More
  • Abstract
  • Literature Map
  • References
  • Citations
  • Similar Papers
Abstract

Given a single RGB image our goal is to label every pixel with an affordance type. By affordance, we mean an object’s capability to readily support a certain human action, without requiring precursor actions. We focus on segmenting the following five affordance types in indoor scenes: ‘walkable’, ‘sittable’, ‘lyable’, ‘reachable’, and ‘movable’. Our approach uses a deep architecture, consisting of a number of multi-scale convolutional neural networks, for extracting mid-level visual cues and combining them toward affordance segmentation. The mid-level cues include depth map, surface normals, and segmentation of four types of surfaces – namely, floor, structure, furniture and props. For evaluation, we augmented the NYUv2 dataset with new ground-truth annotations of the five affordance types. We are not aware of prior work which starts from pixels, infers mid-level cues, and combines them in a feed-forward fashion for predicting dense affordance maps of a single RGB image.

Similar Papers
  • Research Article
  • Citations13

Multi-stage cascaded deconvolution for depth map and surface normal prediction from single image

  • Jul 06, 2018
  • Pattern Recognition Letters
  • Ram Prasad Padhy +4
  • Research Article
  • Citations33

Deep learning for 6D pose estimation of objects — A case study for autonomous driving

  • Mar 16, 2023
  • Expert Systems with Applications
  • Sabera Hoque +4
  • Conference Article
  • Citations120

Putting Humans in a Scene: Learning Affordance in 3D Indoor Environments

  • Jun 01, 2019
  • Xueting Li +5
  • Research Article
  • Citations38

HASIC-Net: Hybrid Attentional Convolutional Neural Network With Structure Information Consistency for Spectral Super-Resolution of RGB Images

  • Jan 01, 2022
  • IEEE Transactions on Geoscience and Remote Sensing
  • Jiaojiao Li +5
  • PDF
  • Research Article
  • Citations46

Deep Architecture With Cross Guidance Between Single Image and Sparse LiDAR Data for Depth Completion

  • Jan 01, 2020
  • IEEE Access
  • Sihaeng Lee +3
  • Research Article
  • Citations4

Wrinkles Realistic Clothing Reconstruction by Combining Implicit and Explicit Method

  • Mar 21, 2023
  • Computer-Aided Design
  • Xinqi Liu +2
  • Research Article
  • Citations26

Animated 3D human avatars from a single image with GAN-based texture inference

  • Jan 29, 2021
  • Computers & Graphics
  • Zhong Li +9
  • PDF
  • Research Article
  • Citations8

Encoder-Decoder Structure With the Feature Pyramid for Depth Estimation From a Single Image

  • Jan 01, 2021
  • IEEE Access
  • Mengxia Tang +3
  • Research Article
  • Citations69

Elderly fall detection based on multi-stream deep convolutional networks

  • Mar 25, 2020
  • Multimedia Tools and Applications
  • Chadia Khraief +2
  • Conference Article
  • Citations12

Learning to Generate Dense Point Clouds with Textures on Multiple Categories

  • Jan 01, 2021
  • Tao Hu +3
  • Research Article
  • Citations13

Variational Object-Aware 3-D Hand Pose From a Single RGB Image

  • Oct 01, 2019
  • IEEE Robotics and Automation Letters
  • Yafei Gao +4
  • PDF
  • Research Article
  • Citations7

Lightweight and Energy-Aware Monocular Depth Estimation Models for IoT Embedded Devices: Challenges and Performances in Terrestrial and Underwater Scenarios †

  • Feb 16, 2023
  • Sensors (Basel, Switzerland)
  • Lorenzo Papa +4
  • PDF
  • Research Article
  • Citations7

Cascaded Hierarchical CNN for RGB-Based 3D Hand Pose Estimation

  • Jul 15, 2020
  • Mathematical Problems in Engineering
  • Shiming Dai +4
  • Conference Article
  • Citations425

DeepHuman: 3D Human Reconstruction From a Single Image

  • Oct 01, 2019
  • Zerong Zheng +4
  • Conference Article
  • Citations1

Two-hand Pose Estimation from the non-cropped RGB Image with Self-Attention Based Network

  • Oct 01, 2021
  • Zhoutao Sun +2
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.