DeepAI AI Chat
Log In Sign Up

Adversarial Inverse Graphics Networks: Learning 2D-to-3D Lifting and Image-to-Image Translation from Unpaired Supervision

by   Hsiao-Yu Fish Tung, et al.
Carnegie Mellon University

Researchers have developed excellent feed-forward models that learn to map images to desired outputs, such as to the images' latent factors, or to other images, using supervised learning. Learning such mappings from unlabelled data, or improving upon supervised models by exploiting unlabelled data, remains elusive. We argue that there are two important parts to learning without annotations: (i) matching the predictions to the input observations, and (ii) matching the predictions to known priors. We propose Adversarial Inverse Graphics networks (AIGNs): weakly supervised neural network models that combine feedback from rendering their predictions, with distribution matching between their predictions and a collection of ground-truth factors. We apply AIGNs to 3D human pose estimation and 3D structure and egomotion estimation, and outperform models supervised by only paired annotations. We further apply AIGNs to facial image transformation using super-resolution and inpainting renderers, while deliberately adding biases in the ground-truth datasets. Our model seamlessly incorporates such biases, rendering input faces towards young, old, feminine, masculine or Tom Cruise-like equivalents (depending on the chosen bias), or adding lip and nose augmentations while inpainting concealed lips and noses.


page 1

page 2

page 7

page 9

page 10

page 14

page 15

page 16


Heuristic Weakly Supervised 3D Human Pose Estimation in Novel Contexts without Any 3D Pose Ground Truth

Monocular 3D human pose estimation from a single RGB image has received ...

Perceptual Adversarial Networks for Image-to-Image Transformation

In this paper, we propose a principled Perceptual Adversarial Networks (...

When the Ground Truth is not True: Modelling Human Biases in Temporal Annotations

In supervised learning, low quality annotations lead to poorly performin...

Weakly Supervised Generative Network for Multiple 3D Human Pose Hypotheses

3D human pose estimation from a single image is an inverse problem due t...

Hand Pose Estimation through Semi-Supervised and Weakly-Supervised Learning

We propose a method for hand pose estimation based on a deep regressor t...

How Bad is Good enough: Noisy annotations for instrument pose estimation

Though analysis of Medical Images by Deep Learning achieves unprecedente...

Synthesizing Programs for Images using Reinforced Adversarial Learning

Advances in deep generative networks have led to impressive results in r...