Tejas D Kulkarni — accepted AI-conference papers

2019

Unsupervised Learning of Object Keypoints for Perception and Control

Tejas D Kulkarni, Ankush Gupta, Catalin Ionescu, Sebastian Borgeaud, Malcolm Reynolds, Andrew Zisserman +1

NeurIPS 2019poster

The study of object representations in computer vision has primarily focused on developing representations that are useful for image classification, object detection, or semantic segmentation as downstream tasks. In this work we aim to learn object representations that are useful for control and rei…

Cited by 235 Source ↗PDF ↗code ↗Scholar ↗

2017

Learning to Perform Physics Experiments via Deep Reinforcement Learning

Misha Denil, Pulkit Agrawal, Tejas D Kulkarni, Tom Erez, Peter Battaglia, Nando de Freitas

ICLR 2017poster

When encountering novel objects, humans are able to infer a wide range of physical properties such as mass, friction and deformability by interacting with them in a goal driven way. This process of active interaction is in the same spirit as a scientist performing experiments to discover hidden fact…

Cited by 91 Source ↗Scholar ↗

2017

Self-Supervised Intrinsic Image Decomposition

Michael Janner, Jiajun Wu, Tejas D Kulkarni, Ilker Yildirim, Josh Tenenbaum

NeurIPS 2017poster

Intrinsic decomposition from a single image is a highly challenging task, due to its inherent ambiguity and the scarcity of training data. In contrast to traditional fully supervised learning approaches, in this paper we propose learning intrinsic image decomposition by explaining the input image. O…

Cited by 143 Source ↗PDF ↗Scholar ↗

2017

Synthesizing 3D Shapes via Modeling Multi-View Depth Maps and Silhouettes With Deep Generative Networks

Amir Arsalan Soltani, Haibin Huang, Jiajun Wu, Tejas D. Kulkarni, Joshua B. Tenenbaum

CVPR 2017poster

We study the problem of learning generative models of 3D shapes. Voxels or 3D parts have been widely used as the underlying representations to build complex 3D shapes; however, voxel-based representations suffer from high memory requirements, and parts-based models require a large collection of cach…

Cited by 256 PDF ↗Scholar ↗

2015

Deep Convolutional Inverse Graphics Network

Tejas D Kulkarni, William F. Whitney, Pushmeet Kohli, Josh Tenenbaum

NeurIPS 2015spotlight

This paper presents the Deep Convolution Inverse Graphics Network (DC-IGN), a model that aims to learn an interpretable representation of images, disentangled with respect to three-dimensional scene structure and viewing transformations such as depth rotations and lighting variations. The DC-IGN mod…

Cited by 1155 Source ↗PDF ↗Scholar ↗

2015

Picture: A Probabilistic Programming Language for Scene Perception

Tejas D. Kulkarni, Pushmeet Kohli, Joshua B. Tenenbaum, Vikash Mansinghka

CVPR 2015poster

Recent progress on probabilistic modeling and statistical learning, coupled with the availability of large training datasets, has led to remarkable progress in computer vision. Generative probabilistic models, or analysis-by-synthesis approaches, can capture rich scene structure but have been less w…

Cited by 250 Source ↗PDF ↗Scholar ↗