DeepAI AI Chat
Log In Sign Up

Multi-View Image-to-Image Translation Supervised by 3D Pose

by   Idit Diamant, et al.

We address the task of multi-view image-to-image translation for person image generation. The goal is to synthesize photo-realistic multi-view images with pose-consistency across all views. Our proposed end-to-end framework is based on a joint learning of multiple unpaired image-to-image translation models, one per camera viewpoint. The joint learning is imposed by constraints on the shared 3D human pose in order to encourage the 2D pose projections in all views to be consistent. Experimental results on the CMU-Panoptic dataset demonstrate the effectiveness of the suggested framework in generating photo-realistic images of persons with new poses that are more consistent across all views in comparison to a standard Image-to-Image baseline. The code is available at:


page 4

page 8

page 9

page 10

page 11


Unsupervised Image-to-Image Translation Networks

Unsupervised image-to-image translation aims at learning a joint distrib...

Specular-to-Diffuse Translation for Multi-View Reconstruction

Most multi-view 3D reconstruction algorithms, especially when shape-from...

Probabilistic Plant Modeling via Multi-View Image-to-Image Translation

This paper describes a method for inferring three-dimensional (3D) plant...

Human Pose Manipulation and Novel View Synthesis using Differentiable Rendering

We present a new approach for synthesizing novel views of people in new ...

UMFuse: Unified Multi View Fusion for Human Editing applications

The vision community has explored numerous pose guided human editing met...

Content and Colour Distillation for Learning Image Translations with the Spatial Profile Loss

Generative adversarial networks has emerged as a defacto standard for im...

3D-Aware Multi-Class Image-to-Image Translation with NeRFs

Recent advances in 3D-aware generative models (3D-aware GANs) combined w...