Indoor Segmentation and Support Inference from RGBD Images

By Nathan Silberman, Derek Hoiem, Pushmeet Kohli, Rob Fergus. 2012

6,680 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition

How researchers see this paper

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

In Computer Vision and Pattern Recognition

Citations in the corpus

Fully convolutional networks for semantic segmentation (2014, methodology): “NYUDv2 [30] is an RGB-D dataset collected using the”
Microsoft COCO: Common Objects in Context (2014, background): “The community has also created datasets containing object attributes [8], scene attributes [9], keypoints [10], and 3D scene information [11].”
Contrastive Multiview Coding (2019, methodology): “her methods; and on HMDB-51, CMC is second-best in performance. 4.3. Extending CMC to More Views We further extend our CMC learning framework to multiview scenarios. We experiment on the NYU-Depth-V2 [42] dataset which consists of 1449 labeled images. We focus more on understanding the behavior and ”
COCO-Stuff: Thing and Stuff Classes in Context (2016, methodology): “In particular, MSRC 21 [46], KITTI [23], CamVid [7], SIFT Flow [36] and NYUD [47] all have less than 5,000 images (Table 1).”
Scaling and Benchmarking Self-Supervised Visual Representation Learning (2019, methodology): “We use the NYUv2 [61] dataset which consists of indoor scenes and use the surface normals calculated by [36].”
Split-Brain Autoencoders: Unsupervised Learning by Cross-Channel Prediction (2016, methodology): “We also test the split-brain autoencoder method on on registered images and depth scans from NYU-D [33].”
Coupled Generative Adversarial Networks (2016, methodology): “Color and Depth Images: We used the RGBD dataset [15] and the NYU dataset [16] for learning joint distribution of color and depth images.”
VizWiz Grand Challenge: Answering Visual Questions from Blind People (2018, methodology): “DAQUAR [28] NYU Depth V2 [34] Automatically generated (templates) ——– VQA v1.”
Vision-and-Language Navigation: Interpreting Visually-Grounded Navigation Instructions in Real Environments (2017, methodology): “ based on the Matterport3D dataset [11]. The Room-to-Room (R2R) navigation dataset is discussed in Section4. 3.1. Matterport3D Dataset Most RGB-D datasets are derived from video sequences; e.g. NYUv2 [42], SUN RGB-D [48] and ScanNet [15]. These datasets typically offer only one or two paths through ”
EDTER: Edge Detection with Transformer (2022, methodology): “We conduct the experiments on three popular benchmarks: BSDS500 [1], NYUDv2 [49] and Multicue [42].”
Ego4D: Around the World in 3,000 Hours of Egocentric Video (2021, background): “[202] Nathan Silberman, Derek Hoiem, Pushmeet Kohli, and Rob Fergus.”
ZeroWaste Dataset: Towards Deformable Object Segmentation in Cluttered Scenes (2021, background): “Detection and Segmentation Datasets Many datasets for image segmentation have been proposed with the goal of densely recognizing general objects and “stuff” in image scenes like street view [7, 17, 61], natural scenes [9, 20, 35, 44,65], and indoor spaces [13,19,53].”
Hypersim: A Photorealistic Synthetic Dataset for Holistic Indoor Scene Understanding (2020, methodology): “We also evaluate sim-to-real transfer performance on two scene understanding tasks – semantic segmentation on NYUv2 [68] and 3D shape prediction on Pix3D [73] – where we ﬁnd that pre-training on our dataset signiﬁcantly improves performance on both tasks, and achieves state-of-the-art performance…”
Object-Proposal Evaluation Protocol is ‘Gameable’ (2015, methodology): “NYU-Depth V2: NYU-Depth V2 dataset [65] is comprised of video sequences from a variety of indoor scenes as recorded by both the RGB and Depth cameras.”
Holistically-Nested Edge Detection (2015, background): “NYUDv2 Dataset The NYU Depth (NYUD) dataset [33] has 1449 RGB-D images.”
Fast Edge Detection Using Structured Forests (2014, neutral): “F”