Timezone: »
Poster
PixelTransformer: Sample Conditioned Signal Generation
Shubham Tulsiani · Abhinav Gupta
We propose a generative model that can infer a distribution for the underlying spatial signal conditioned on sparse samples e.g. plausible images given a few observed pixels. In contrast to sequential autoregressive generative models, our model allows conditioning on arbitrary samples and can answer distributional queries for any location. We empirically validate our approach across three image datasets and show that we learn to generate diverse and meaningful samples, with the distribution variance reducing given more observed pixels. We also show that our approach is applicable beyond images and can allow generating other types of spatial outputs e.g. polynomials, 3D shapes, and videos.
Author Information
Shubham Tulsiani (Facebook AI Research)
Abhinav Gupta (Carnegie Mellon University)
Related Events (a corresponding poster, oral, or spotlight)
-
2021 Spotlight: PixelTransformer: Sample Conditioned Signal Generation »
Tue. Jul 20th 02:30 -- 02:35 PM Room
More from the Same Authors
-
2020 : Neural Dynamic Policies for End-to-End Sensorimotor Learning »
Abhinav Gupta -
2020 Poster: Learning Robot Skills with Temporal Variational Inference »
Tanmay Shankar · Abhinav Gupta -
2019 Poster: Self-Supervised Exploration via Disagreement »
Deepak Pathak · Dhiraj Gandhi · Abhinav Gupta -
2019 Oral: Self-Supervised Exploration via Disagreement »
Deepak Pathak · Dhiraj Gandhi · Abhinav Gupta -
2017 Poster: Robust Adversarial Reinforcement Learning »
Lerrel Pinto · James Davidson · Rahul Sukthankar · Abhinav Gupta -
2017 Talk: Robust Adversarial Reinforcement Learning »
Lerrel Pinto · James Davidson · Rahul Sukthankar · Abhinav Gupta