• Publications
  • Influence
3D ShapeNets: A deep representation for volumetric shapes
tl;dr
We propose to represent a geometric 3D shape as a probability distribution of binary variables on a 3D voxel grid, using a Convolutional Deep Belief Network. Expand
  • 1,815
  • 475
  • Open Access
ShapeNet: An Information-Rich 3D Model Repository
tl;dr
We present ShapeNet: a richly-annotated, large-scale repository of shapes represented by 3D CAD models of objects. Expand
  • 1,408
  • 362
  • Open Access
SUN RGB-D: A RGB-D scene understanding benchmark suite
tl;dr
We introduce a RGB-D benchmark suite at PASCAL VOC scale with annotation in both 2D and 3D, for both objects and rooms. Expand
  • 647
  • 172
  • Open Access
LSUN: Construction of a Large-scale Image Dataset using Deep Learning with Humans in the Loop
tl;dr
We propose to amplify human effort through a partially automated labeling scheme, leveraging deep learning with humans in the loop. Expand
  • 533
  • 119
  • Open Access
Semantic Scene Completion from a Single Depth Image
tl;dr
We introduce the semantic scene completion network (SSCNet), an end-to-end 3D convolutional network that takes a single depth image as input and simultaneously outputs occupancy and semantic labels for all voxels in the view frustum. Expand
  • 511
  • 113
  • Open Access
Matterport3D: Learning from RGB-D Data in Indoor Environments
tl;dr
We introduce Matterport3D, a large-scale RGB-D dataset containing 10,800 panoramic views from 194,400RGB-D images of 90 building-scale scenes. Expand
  • 343
  • 65
  • Open Access
Deep Sliding Shapes for Amodal 3D Object Detection in RGB-D Images
  • Shuran Song, J. Xiao
  • Computer Science
  • IEEE Conference on Computer Vision and Pattern…
  • 7 November 2015
tl;dr
We focus on the task of amodal 3D object detection in RGB-D images, which aims to produce a 3D bounding box of an object in metric form at its full extent. Expand
  • 396
  • 54
  • Open Access
Tracking Revisited Using RGBD Camera: Unified Benchmark and Baselines
  • Shuran Song, J. Xiao
  • Computer Science
  • IEEE International Conference on Computer Vision
  • 1 December 2013
tl;dr
We construct a unified benchmark dataset of 100 RGBD videos with high diversity, propose different kinds of RGBD tracking algorithms using 2D or 3D model, and present a quantitative comparison of various algorithms with RGB or RGBD input. Expand
  • 219
  • 53
  • Open Access
3DMatch: Learning Local Geometric Descriptors from RGB-D Reconstructions
tl;dr
In this paper, we present 3DMatch, a data-driven model that learns a local volumetric patch descriptor for establishing correspondences between partial 3D data. Expand
  • 249
  • 43
  • Open Access
Sliding Shapes for 3D Object Detection in Depth Images
tl;dr
We propose to use depth maps for object detection and design a 3D detector to overcome the major difficulties for recognition, namely the variations of texture, illumination, shape, viewpoint, clutter, occlusion and sensor noises. Expand
  • 294
  • 30
  • Open Access