Search Results for author: Rahul Venkatesh

Found 6 papers, 1 papers with code

Self-Supervised Learning of Motion Concepts by Optimizing Counterfactuals

no code implementations25 Mar 2025 Stefan Stojanov, David Wendt, Seungwoo Kim, Rahul Venkatesh, Kevin Feigelis, Jiajun Wu, Daniel LK Yamins

Estimating motion in videos is an essential computer vision problem with many downstream applications, including controllable video generation and robotics.

counterfactual Motion Estimation +3

Unifying (Machine) Vision via Counterfactual World Modeling

no code implementations2 Jun 2023 Daniel M. Bear, Kevin Feigelis, Honglin Chen, Wanhee Lee, Rahul Venkatesh, Klemen Kotar, Alex Durango, Daniel L. K. Yamins

Leading approaches in machine vision employ different architectures for different tasks, trained on costly task-specific labeled datasets.

counterfactual Optical Flow Estimation

Deep Implicit Surface Point Prediction Networks

no code implementations ICCV 2021 Rahul Venkatesh, Tejan Karmali, Sarthak Sharma, Aurobrata Ghosh, R. Venkatesh Babu, László A. Jeni, Maneesh Singh

Unsigned distance function (UDF) based approaches have been proposed recently as a promising alternative to represent both open and closed shapes.

Prediction

DUDE: Deep Unsigned Distance Embeddings for Hi-Fidelity Representation of Complex 3D Surfaces

no code implementations4 Nov 2020 Rahul Venkatesh, Sarthak Sharma, Aurobrata Ghosh, Laszlo Jeni, Maneesh Singh

Several implicit 3D shape representation approaches using deep neural networks have been proposed leading to significant improvements in both quality of representations as well as the impact on downstream applications.

3D Shape Representation

Cannot find the paper you are looking for? You can Submit a new open access paper.