• Publications
  • Influence
Opt
Many graphics and vision problems can be expressed as non-linear least squares optimizations of objective functions over visual data, such as images and meshes. The mathematical descriptions of theseExpand
ScanNet: Richly-Annotated 3D Reconstructions of Indoor Scenes
TLDR
We introduce ScanNet, an RGB-D video dataset containing 2.5M views in 1513 scenes annotated with 3D camera poses, surface reconstructions, and semantic segmentations. Expand
FaceForensics++: Learning to Detect Manipulated Facial Images
TLDR
The rapid progress in synthetic image generation and manipulation has now come to a point where it raises significant concerns for the implications towards society. Expand
Face2Face: real-time face capture and reenactment of RGB videos
TLDR
We present Face2Face, a novel approach for real-time facial reenactment of a monocular target video sequence (e.g., Youtube video). Expand
Volumetric and Multi-view CNNs for Object Classification on 3D Data
TLDR
In this paper, we aim to improve both volumetric CNNs and multi-view CNNs according to extensive analysis of existing approaches for object classification on 3D data. Expand
Matterport3D: Learning from RGB-D Data in Indoor Environments
TLDR
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
Real-time 3D reconstruction at scale using voxel hashing
TLDR
We contribute an online system for large and fine scale volumetric reconstruction based on a memory and speed efficient data structure. Expand
BundleFusion: real-time globally consistent 3D reconstruction using on-the-fly surface re-integration
TLDR
Real-time, high-quality, 3D scanning of large-scale scenes is key to mixed reality and robotic applications. Expand
3DMatch: Learning Local Geometric Descriptors from RGB-D Reconstructions
TLDR
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
Shape Completion Using 3D-Encoder-Predictor CNNs and Shape Synthesis
TLDR
We introduce a data-driven approach to complete partial 3D shapes through a combination of volumetric deep neural networks and 3D shape synthesis. Expand
...
1
2
3
4
5
...