822 citations · 2.4k across the 23 of their papers we have counts for
6 papers · 1 filter
Unsupervised Doodling and Painting with Improved SPIRAL
John F. J. Mellor, Eunbyung Park, Yaroslav Ganin +7
We investigate using reinforcement learning agents as generative models of images (extending arXiv:1804.01118). A generative agent controls a simulated painting environment, and is…
Unsupervised Learning of Object Keypoints for Perception and Control
Tejas Kulkarni, Ankush Gupta, Catalin Ionescu +4
The study of object representations in computer vision has primarily focused on developing representations that are useful for image classification, object detection, or semantic s…
Synthesizing Programs for Images using Reinforced Adversarial Learning
Yaroslav Ganin, Tejas Kulkarni, Igor Babuschkin +2
Advances in deep generative networks have led to impressive results in recent years. Nevertheless, such models can often waste their capacity on the minutiae of datasets, presumabl…
Self-Supervised Intrinsic Image Decomposition
Michael Janner, Jiajun Wu, Tejas D. Kulkarni +2
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 supervis…
Deep Convolutional Inverse Graphics Network
Tejas D. Kulkarni, Will Whitney, Pushmeet Kohli +1
This paper presents the Deep Convolution Inverse Graphics Network (DC-IGN), a model that learns an interpretable representation of images. This representation is disentangled with…
Inverse Graphics with Probabilistic CAD Models
Tejas D. Kulkarni, Vikash K. Mansinghka, Pushmeet Kohli +1
Recently, multiple formulations of vision problems as probabilistic inversions of generative models based on computer graphics have been proposed. However, applications to 3D perce…