Indoor Scene Understanding with RGB-D Images: Bottom-up Segmentation, Object Detection and Semantic Segmentation

By Saurabh Gupta, Pablo Arbeláez, Ross B. Girshick, Jitendra Malik. 2015

264 citations recorded by the source corpus.

Subfields: Aerospace Engineering, Computer Vision and Pattern Recognition, 3D Vision & Pose

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Aerospace Engineering

In Computer Vision and Pattern Recognition

In 3D Vision & Pose

Citations in the corpus

NTU RGB+D 120: A Large-Scale Benchmark for 3D Human Activity Understanding (2019, background): “This empowers the computer vision solutions to move important steps towards 3D vision, such as 3D object recognition [2], 3D scene understanding [3], and 3D activity analysis [4], etc .”
Deep Convolutional Neural Networks for Computer-Aided Detection: CNN Architectures, Dataset Characteristics and Transfer Learning (2016, background): “Finally, transfer learning in CNN representation, as empirically verified in previous literature [59]–[61], [11], [62] can be effective in various cross-modality imaging settings (RGB images to depth images [59], [60], natural images to general CT and MRI images [11], and natural images to neuroimag”
Inferring 3D Object Pose in RGB-D Images (2015, methodology): “[11, 17, 34, 35] propose modification to deformable part models [7] to adapt them to the RGB-D domain.”
Centroid Based Concept Learning for RGB-D Indoor Scene Classification (2019, background): “In an early approach, [10] proposed to extract local features by quantizing segmentation outputs and detecting contours on depth images.”
Superpixels: An evaluation of the state-of-the-art (2016, methodology): “We found that UE tends to correlate strongly with ASA which can be explained by Equations (3) and (6), respectively.”
Aligning 3D models to RGB-D images of cluttered scenes (2015, methodology): “Modifications to deformable part models [7] for RGB-D images were proposed in [11, 17, 35, 36].”
Learning in high-dimensional multimedia data: the state of the art (2015, background): “It has been widely researched in different fields including statistics and machine learning, with applications on object recognition [4, 24, 25], data analysis and visualizations [71], and many others [12, 16].”
3D Graph Neural Networks for RGBD Semantic Segmentation (2017, unknown): “[10] (2015) 30.”
Dynamic Fusion Module Evolves Drivable Area and Road Anomaly Detection: A Benchmark and Algorithms (2021, background): “[31] combined RGB images with normal information for multiple tasks, including contour classifica-”
Deep Learning and Convolutional Neural Networks for Medical Image Computing (2017, methodology): “Finally, transfer learning in CNN representation, as empirically verified in previous literature [11, 57–60], can be effective in various cross-modality imaging settings (RGB images to depth images [57, 58], natural images to general CT andMRI images [11], and natural images to neuroimaging [59] or ”