A
Anurag Ranjan
Researcher at Max Planck Society
Publications - 40
Citations - 3264
Anurag Ranjan is an academic researcher from Max Planck Society. The author has contributed to research in topics: Computer science & Optical flow. The author has an hindex of 12, co-authored 30 publications receiving 1846 citations. Previous affiliations of Anurag Ranjan include Harvard University & University of British Columbia.
Papers
More filters
Proceedings ArticleDOI
Optical Flow Estimation Using a Spatial Pyramid Network
Anurag Ranjan,Michael J. Black +1 more
TL;DR: The Spatial Pyramid Network (SPyNet) is much simpler and 96% smaller than FlowNet in terms of model parameters, which makes it more efficient and appropriate for embedded applications.
Proceedings ArticleDOI
Competitive Collaboration: Joint Unsupervised Learning of Depth, Camera Motion, Optical Flow and Motion Segmentation
TL;DR: In this article, the authors propose a competitive collaboration framework that facilitates the coordinated training of multiple specialized neural networks to solve complex low-level vision problems, such as single view depth prediction, camera motion estimation, optical flow, and segmentation of a video into the static scene and moving regions.
Book ChapterDOI
Generating 3D Faces using Convolutional Mesh Autoencoders
TL;DR: In this article, spectral convolutions on a mesh surface are used to learn a non-linear representation of a face using mesh sampling operations that enable a hierarchical mesh representation that captures nonlinear variations in shape and expression at multiple scales within the model.
Proceedings ArticleDOI
Learning to Dress 3D People in Generative Clothing
Qianli Ma,Jinlong Yang,Anurag Ranjan,Sergi Pujades,Gerard Pons-Moll,Siyu Tang,Michael J. Black +6 more
TL;DR: This work learns a generative 3D mesh model of clothed people from 3D scans with varying pose and clothing, and is the first generative model that directly dresses 3D human body meshes and generalizes to different poses.
Book ChapterDOI
Unsupervised Learning of Multi-Frame Optical Flow with Occlusions
TL;DR: This paper exploits the minimal configuration of three frames to strengthen the photometric loss and explicitly reason about occlusions and demonstrates that their multi-frame, occlusion-sensitive formulation outperforms existing unsupervised two-frame methods and even produces results on par with some fully supervised methods.