Title
MISC: Multi-Condition Injection and Spatially-Adaptive Compositing for Conditional Person Image Synthesis
Abstract
In this paper, we explore synthesizing person images with multiple conditions for various backgrounds. To this end, we propose a framework named \"MISC\" for conditional image generation and image compositing. For conditional image generation, we improve the existing condition injection mechanisms by leveraging the inter-condition correlations. For the image compositing, we theoretically prove the weaknesses of the cutting-edge methods, and make it more robust by removing the spatially-invariance constraint, and enabling the bounding mechanism and the spatial adaptability. We show the effectiveness of our method on the Video Instance-level Parsing dataset, and demonstrate the robustness through controllability tests.
Year
DOI
Venue
2020
10.1109/CVPR42600.2020.00776
CVPR
DocType
Citations 
PageRank 
Conference
0
0.34
References 
Authors
13
5
Name
Order
Citations
PageRank
Shuchen Weng101.69
Wenbo Li21129.31
Dawei Li36010.43
Hongxia Jin463367.53
Boxin Shi538145.76