• Publications
  • Influence
3D-R2N2: A Unified Approach for Single and Multi-view 3D Object Reconstruction
TLDR
Inspired by the recent success of methods that employ shape priors to achieve robust 3D reconstructions, we propose a novel recurrent neural network architecture that we call the 3D Recurrent Reconstruction Neural Network. Expand
Generalized Intersection Over Union: A Metric and a Loss for Bounding Box Regression
TLDR
In this paper, we address the this weakness by introducing a generalized version of IoU as both a new loss and a new metric. Expand
4D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networks
TLDR
In many robotics and VR/AR applications, 3D-videos are readily-available input sources (a sequence of depth images, or LIDAR scans). Expand
Universal Correspondence Network
TLDR
We present a deep learning framework for accurate visual correspondences and demonstrate its effectiveness for both geometric and semantic matching, spanning across rigid motions to intra-class shape variations. Expand
SEGCloud: Semantic Segmentation of 3D Point Clouds
TLDR
We present SEGCloud, an end-to-end framework to obtain 3D point-level segmentation that combines the advantages of NNs, trilinear interpolation(TI) and fully connected Conditional Random Fields (FC-CRF) to obtain fine-grained 3D Segmentation. Expand
DeformNet: Free-Form Deformation Network for 3D Shape Reconstruction from a Single Image
TLDR
We introduce a new differentiable layer for 3D data deformation and use it in DEFORMNET to learn a model for3D reconstruction-through-deformation. Expand
3D Scene Graph: A Structure for Unified Semantics, 3D Space, and Camera
A comprehensive semantic understanding of a scene is important for many applications - but in what space should diverse semantic information (e.g., objects, scene categories, material types, 3DExpand
Completing 3D object shape from one depth image
TLDR
We take an exemplar-based approach: retrieve similar objects in a database of 3D models using view-based matching and transfer the symmetries from retrieved models. Expand
JRDB: A Dataset and Benchmark for Visual Perception for Navigation in Human Environments
TLDR
We present JRDB, a novel dataset collected from our social mobile manipulator JackRabbot. Expand
Weakly Supervised 3D Reconstruction with Adversarial Constraint
TLDR
This paper presents a framework for volumetric shape reconstruction using silhouettes (foreground mask) from a single or sparse set of viewpoints as input. Expand
...
1
2
...