Marginal Contrastive Correspondence for Guided Image Generation
Fangneng Zhan, Yingchen Yu, Rongliang Wu, Jiahui Zhang, Shijian Lu, Changgong Zhang
Abstract
Exemplar-based image translation establishes dense correspondences between a conditional input and an exemplar (from two different domains) for leveraging detailed exemplar styles to achieve realistic image translation. Existing work builds the cross-domain correspondences implicitly by minimizing feature-wise distances across the two domains. Without explicit exploitation of domain-invariant features, this approach may not reduce the domain gap effectively which often leads to sub-optimal correspondences and image translation. We design a Marginal Contrastive Learning Network (MCL-Net) that explores contrastive learning to learn domain-invariant features for realistic exemplar-based image translation. Specifically, we design an innovative marginal contrastive loss that guides to establish dense correspondences explicitly. Nevertheless, building correspondence with domain-invariant semantics alone may impair the texture patterns and lead to degraded texture generation. We thus design a Self-Correlation Map (SCM) that incorporates scene structures as auxiliary information which improves the built correspondences substantially. Quantitative and qualitative experiments on multifarious image translation tasks show that the proposed method outperforms the state-of-the-art consistently.
Create a lesson
Related papers
Seeing the Small: Deformable Duality Mamba for Retinal Lesion Segmentation
Chang Yu, Siqing Li, Yuanchen Liu et al.
Evidential Deep Learning with conditional entropy for glaucoma detection
Hai Siong Tan, Kuancheng Wang
TMAL: Topology-preserving Multi-offset Affinity Learning for Curvilinear Structure Segmentation
Suho Han, Soungsill Park, Kanghyun Ryu et al.
Distribution Shift Detection in Remote Sensing Imagery using Machine Learning Models
Abdullah Almansour, Ozan K. Tonguz
Dark Matters: VAE-Aware HDR Encoding for SDR-to-HDR Video Reconstruction
Donghoon Cha, Bomseok Park, Hansl von Kwon et al.
Reasoning-Aware Relational Representation Learning for Open-Vocabulary Scene Graph Generation
Jiawei Xiao, Boya Wang, Longtian Qiu et al.