Semantic I2I - Paper Copilot

Jihye Park, Sunwoo Kim, Soohyun Kim, Seokju Cho, Jaejun Yoo, Youngjung Uh, Seungryong Kim

Korea University; UNIST; Yonsei University

Portals

Abstract

Existing techniques for image-to-image translation commonly have suffered from two critical problems: heavy reliance on per-sample domain annotation and/or inability of handling multiple attributes per image. Recent truly-unsupervised methods adopt clustering approaches to easily provide per-sample one-hot domain labels. However, they cannot account for the real-world setting: one sample may have multiple attributes. In addition, the semantics of the clusters are not easily coupled to the human understanding. To overcome these, we present a LANguage-driven Image-to-image Translation model, dubbed LANIT. We leverage easy-to-obtain candidate attributes given in texts for a dataset: the similarity between images and attributes indicates per-sample domain labels. This formulation naturally enables multi-hot label so that users can specify the target domain with a set of attributes in language. To account for the case that the initial prompts are inaccurate, we also present prompt learning. We further present domain regularization loss that enforces translated images be mapped to the corresponding domain. Experiments on several standard benchmarks demonstrate that LANIT achieves comparable or superior performance to existing models.

Taesung Park, Ming-Yu Liu, Ting-Chun Wang, Jun-Yan Zhu

UC Berkeley; NVIDIA; MIT CSAIL

Portals

Abstract

We propose spatially-adaptive normalization, a simple but effective layer for synthesizing photorealistic images given an input semantic layout. Previous methods directly feed the semantic layout as input to the deep network, which is then processed through stacks of convolution, normalization, and nonlinearity layers. We show that this is suboptimal as the normalization layers tend to ``wash away'' semantic information. To address the issue, we propose using the input layout for modulating the activations in normalization layers through a spatially-adaptive, learned transformation. Experiments on several challenging datasets demonstrate the advantage of the proposed method over existing approaches, regarding both visual fidelity and alignment with input layouts. Finally, our model allows user control over both semantic and style. Code is available at https://github.com/NVlabs/SPADE .

Category: Semantic I2I

LANIT: Language-Driven Image-to-Image Translation for Unlabeled Data

Portals

Abstract

GauGAN: Semantic Image Synthesis with Spatially-Adaptive Normalization

Portals

Abstract