GANzzle: Reframing jigsaw puzzle solving as a retrieval task using a generative mental image

07/12/2022
by   Davide Talon, et al.
0

Puzzle solving is a combinatorial challenge due to the difficulty of matching adjacent pieces. Instead, we infer a mental image from all pieces, which a given piece can then be matched against avoiding the combinatorial explosion. Exploiting advancements in Generative Adversarial methods, we learn how to reconstruct the image given a set of unordered pieces, allowing the model to learn a joint embedding space to match an encoding of each piece to the cropped layer of the generator. Therefore we frame the problem as a R@1 retrieval task, and then solve the linear assignment using differentiable Hungarian attention, making the process end-to-end. In doing so our model is puzzle size agnostic, in contrast to prior deep learning methods which are single size. We evaluate on two new large-scale datasets, where our model is on par with deep learning methods, while generalizing to multiple puzzle sizes.

READ FULL TEXT

page 2

page 4

page 7

page 9

research
06/09/2021

Phase Retrieval using Single-Instance Deep Generative Prior

Several deep learning methods for phase retrieval exist, but most of the...
research
11/27/2018

Perceptual Conditional Generative Adversarial Networks for End-to-End Image Colourization

Colours are everywhere. They embody a significant part of human visual p...
research
12/11/2019

Concept and Experimental Demonstration of Optical IM/DD End-to-End System Optimization using a Generative Model

We perform an experimental end-to-end transceiver optimization via deep ...
research
12/10/2019

Phase Retrieval using Conditional Generative Adversarial Networks

In this paper, we propose the application of conditional generative adve...
research
06/03/2020

Multiple Generative Adversarial Networks Analysis for Predicting Photographers' Retouching

Anyone can take a photo, but not everybody has the ability to retouch th...
research
11/26/2017

Unsupervised 3D Reconstruction from a Single Image via Adversarial Learning

Recent advancements in deep learning opened new opportunities for learni...

Please sign up or login with your details

Forgot password? Click here to reset