Semi-parametric Image Synthesis

04/29/2018
by   Xiaojuan Qi, et al.
2

We present a semi-parametric approach to photographic image synthesis from semantic layouts. The approach combines the complementary strengths of parametric and nonparametric techniques. The nonparametric component is a memory bank of image segments constructed from a training set of images. Given a novel semantic layout at test time, the memory bank is used to retrieve photographic references that are provided as source material to a deep network. The synthesis is performed by a deep network that draws on the provided photographic material. Experiments on multiple semantic segmentation datasets show that the presented approach yields considerably more realistic images than recent purely parametric techniques. The results are shown in the supplementary video at https://youtu.be/U4Q98lenGLQ

READ FULL TEXT

page 2

page 3

page 4

page 5

page 8

research
08/15/2022

Memory-Driven Text-to-Image Generation

We introduce a memory-driven semi-parametric approach to text-to-image g...
research
07/08/2018

Semi-parametric Image Inpainting

This paper introduces a semi-parametric approach to image inpainting for...
research
07/28/2017

Photographic Image Synthesis with Cascaded Refinement Networks

We present an approach to synthesizing photographic images conditioned o...
research
07/24/2019

Semi-parametric Object Synthesis

We present a new semi-parametric approach to synthesize novel views of a...
research
03/04/2022

Semi-parametric Makeup Transfer via Semantic-aware Correspondence

The large discrepancy between the source non-makeup image and the refere...
research
03/15/2021

Deep Consensus Learning

Both generative learning and discriminative learning have recently witne...
research
09/15/2021

Image Synthesis via Semantic Composition

In this paper, we present a novel approach to synthesize realistic image...

Please sign up or login with your details

Forgot password? Click here to reset