Unsupervised feature learning for 3D scene labeling

By Kevin Lai, Liefeng Bo, Dieter Fox. 2014

382 citations recorded by the source corpus.

Subfields: Computational Mechanics, Computer Vision and Pattern Recognition, Geology, Representation & Self-Supervised Learning, 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 Computational Mechanics

In Computer Vision and Pattern Recognition

In Geology

In Representation & Self-Supervised Learning

In 3D Vision & Pose

Citations in the corpus

Ego4D: Around the World in 3,000 Hours of Egocentric Video (2021, background): “nition [23, 85, 126, 155] to deal with video (frequent FoV changes, objects entering/exiting the view) and to reason about objects in the context of a 3D environment.”
3D fully convolutional network for vehicle detection in point cloud (2016, methodology): “osal Network (RPN) [26]. For the classiﬁcation stage, research have been drawn to features including shape model [6], [13] and geometry statistic features [22], [27], [29], [31]. Sparsing coding [4], [15] and deep learning [26] are also used for feature representation. Besides directly operating in ”
Vehicle Detection from 3D Lidar Using Fully Convolutional Network (2016, methodology): “Besides the hand-crafted features, Deuge et al. [4], Lai et al. [15] explore to learn feature representation of point cloud via sparse coding.”
Deep Sliding Shapes for Amodal 3D Object Detection in RGB-D Images (2015, methodology): “3D Feature Learning HMP3D [14] introduced a hierarchical sparse coding technique for unsupervised learning features from RGB-D images and 3D point cloud data.”
Semantic Scene Completion from a Single Depth Image (2016, background): “Many prior works focus on RGB-D image segmentation [6, 26, 29, 15].”
VConv-DAE: Deep Volumetric Shape Learning Without Object Labels (2016, methodology): “Recently, Lai et al. [8] propose a sparse coding method for learning hierarchical feature representations over 3D point clouds.”
Past, Present, and Future of Simultaneous Localization and Mapping: Toward the Robust-Perception Age (2016, neutral): “If SLAM has to work “out of the box” in arbitrary scenarios, methods for automatic tuning of the involved parameters need to be considered.”
Aligning 3D models to RGB-D images of cluttered scenes (2015, background): “There have been corresponding works for RGB-D images studying the problems of object detection [4, 13, 17, 20, 21, 22, 24, 34, 35, 36], semantic segmentation [3, 12, 13, 19, 25, 32, 33], and more recently instance segmentation [13, 33].”
Robobarista: Object Part Based Transfer of Manipulation Trajectories from Crowd-Sourcing in 3D Pointclouds (2015, background): “There has been great advancement in scene understanding [31, 41, 26, 61], in human activity detection [51, 19], and in features for RGB-D images and point-clouds [47, 29].”
SceneNN: A Scene Meshes Dataset with aNNotations (2016, background): “RGB-D v2 [17] 17 scenes All Cloud Y R O”
PREDATOR: Registration of 3D Point Clouds with Low Overlap (2020, methodology): “…3DMatch : [56] is a collection of 62 scenes, combining earlier data from Analysis-by-Synthesis [44], 7Scenes [37], SUN3D [51], RGB-D Scenes v.2 [25] The dataset was captured using a Velo-dyne HDL-64 3D laser scanner by driving around the mid-size city of Karlsruhe, in rural areas and on…”
A dataset for developing and benchmarking active vision (2017, background): “While other datasets do sample multiple images per scene, they often sample either from just a few positions or along only a few paths through the environment [1], [2].”
Multiview RGB-D Dataset for Object Instance Detection (2016, methodology): “Additionally, we investigate the performance of the Turntable baseline on the WRGB-D Scenes dataset [15].”
WaterGAN: Unsupervised Generative Network to Enable Real-Time Color Correction of Monocular Underwater Images (2017, methodology): “As input in-air RGB-D for all experiments, we compile four indoor Kinect datasets (B3DO [22], UW RGB-D Object [23], NYU Depth [24] and Microsoft 7-scenes [25]) for a total of 15000 RGB-D images.”
PPF-FoldNet: Unsupervised Learning of Rotation Invariant 3D Local Descriptors (2018, methodology): “This dataset is a large ensemble of the existing ones such as Analysis-by-Synthesis [41], 7 -Scenes [37], SUN 3 D [47], RGB-D Scenes v.2 [22] and Halber and Funkhouser [12].”
FoldingNet: Point Cloud Auto-Encoder via Deep Grid Deformation (2017, background): “Applications of learning on point clouds include shape completion and recognition [57], unmanned autonomous vehicles [36], 3D object detection, recognition and classification [9, 33, 40, 41, 48, 49, 53], contour detection [21], layout inference [18], scene labeling [31], category discovery [60], poi”
CoFiNet: Reliable Coarse-to-fine Correspondences for Robust Point Cloud Registration (2021, neutral): “A.4 Data 3DMatch and 3DLoMatch 3DMatch [6] collects 62 scenes from SUN3D [45], 7-Scenes [46], RGB-D Scenes v.2 [47], Analysis-by-Synthesis [48], BundleFusion [49] and Halbel et al. [50], where 46 scenes are used for training, 8 scenes for validation and 8 scenes for testing.”
PPFNet: Global Context Aware Local Features for Robust 3D Point Matching (2018, background): “…on real sets rather than synthetic ones and therefore our evaluations are against the diverse 3DMatch RGBD benchmark [49], in which 62 different real-world scenes retrieved from the pool of datasets Analysis-by-Synthesis [43], 7-Scenes [39], SUN3D [47], RGB-D Scenes v.2 [28] and Halber et [16].”