InstaFormer: Instance-aware Image-to-Image Translation with Transformer
CVPR'22
Soohyun Kim1
Jongbeom Baek1
Jihye Park1
Gyeongnyeon Kim1
Seungryong Kim1
Korea University1
[Paper]
[GitHub]


Abstract

We present a novel Transformer-based network architecture for instance-aware image-to-image translation, dubbed InstaFormer, to effectively integrate global- and instance-level information. By considering extracted content features from an image as tokens, our networks discover global consensus of content features by considering context information through a self-attention module in Transformers. By augmenting such tokens with an instance-level feature extracted from the content feature with respect to bounding box information, our framework is capable of learning an interaction between object instances and the global image, thus boosting the instance-awareness. We replace layer normalization (LayerNorm) in standard Transformers with adaptive instance normalization (AdaIN) to enable a multi-modal translation with style codes. In addition, to improve the instance-awareness and translation quality at object regions, we present an instance-level content contrastive loss defined between input and translated image. We conduct experiments to demonstrate the effectiveness of our InstaFormer over the latest methods and provide extensive ablation studies.


Overall Architecture for InstaFormer

Our networks consist of content encoder, Transformer encoder, and generator. The gray background represents the test phase, where we have no access on object instance bounding box.


ViT Encoder Block

Our ViT encoder block in details: it contains AdaIN layer instead of LayerNorm.


Qualitative Results

Image Translation (INIT)

Domain Adaptation (KITTI → CityScapes)



Paper and Supplementary Material

S. Kim, J. Baek, J. Park, G. Kim, S. Kim
InstaFormer: Instance-aware Image-to-Image Translation with Transformer
in CVPR, 2022.
(hosted on ArXiv)


[Bibtex]


Acknowledgements

This template was originally made by Phillip Isola and Richard Zhang for a colorful ECCV project; the code can be found here.