Continuous and Diverse Image-to-Image Translation via Signed Attribute Vectors

  title={Continuous and Diverse Image-to-Image Translation via Signed Attribute Vectors},
  author={Qi Mao and Hsin-Ying Lee and Hung-Yu Tseng and Jia-Bin Huang and Siwei Ma and Ming-Hsuan Yang},
  journal={Int. J. Comput. Vis.},
Recent image-to-image (I2I) translation algorithms focus on learning the mapping from a source to a target domain. However, the continuous translation problem that synthesizes intermediate results between the two domains has not been well-studied in the literature. Generating a smooth sequence of intermediate results bridges the gap of two different domains, facilitating the morphing effect across domains. Existing I2I approaches are limited to either intra-domain or deterministic inter-domain… 
Beyond a Video Frame Interpolator: A Space Decoupled Learning Approach to Continuous Image Transition
This work rethink the VFI problem and formulate it as a continuous image transition (CIT) task, whose key issue is to transition an image from one space to another space continuously, and proposes space decoupled learning (SDL) approach, which provides an effective framework to a variety of CIT problems beyond VFI.
CoMoGAN: continuous model-guided image-to-image translation
A new Functional Instance Normalization layer and residual mechanism are introduced, which together disentangle image content from position on target manifold, which relies on naive physics-inspired models to guide the training while allowing private model/translations features.
Day to Night Image Style Transfer with Light Control
This work addresses the challenging problem of data augmentation and proposes a novel approach in day-to-night image translation with 3Daware light control that is on par or even outperforms competitive state-of-the-art methods for image translation.
Image Generation using Continuous Filter Atoms
By further modeling filters atoms with a neural ODE, it is shown both empirically and theoretically that such introduced continuity can be propagated to the generated images, and thus achieves gradually evolved image generation.


Homomorphic Latent Space Interpolation for Unpaired Image-To-Image Translation
This paper proposes an alternative framework, as an extension of latent space interpolation, to consider the intermediate region between two domains during translation, based on the fact that in a flat and smooth latent space, there exist many paths that connect two sample points.
Multi-mapping Image-to-Image Translation via Learning Disentanglement
A novel unified model is proposed, which bridges the one-to-many mapping from two aspects: multi-modal translation and multi-domain translation and outperforms state-of-the-art methods.
StarGAN: Unified Generative Adversarial Networks for Multi-domain Image-to-Image Translation
A unified model architecture of StarGAN allows simultaneous training of multiple datasets with different domains within a single network, which leads to StarGAN's superior quality of translated images compared to existing models as well as the novel capability of flexibly translating an input image to any desired target domain.
RelGAN: Multi-Domain Image-to-Image Translation via Relative Attributes
RelGAN is a new method for multi-domain image-to-image translation that is capable of modifying images by changing particular attributes of interest in a continuous manner while preserving the other attributes.
CrDoCo: Pixel-Level Domain Transfer With Cross-Domain Consistency
A novel pixel-wise adversarial domain adaptation algorithm that leverages image-to-image translation methods for data augmentation and introduces a cross-domain consistency loss that enforces the adapted model to produce consistent predictions.
TransGaGa: Geometry-Aware Unsupervised Image-To-Image Translation
A novel disentangle-and-translate framework to tackle the complex objects image-to-image translation task, which disentangles image space into a Cartesian product of the appearance and the geometry latent spaces and supports multimodal translation.
Toward Multimodal Image-to-Image Translation
This work aims to model a distribution of possible outputs in a conditional generative modeling setting that helps prevent a many-to-one mapping from the latent code to the output during training, also known as the problem of mode collapse.
Few-Shot Unsupervised Image-to-Image Translation
This model achieves this few-shot generation capability by coupling an adversarial training scheme with a novel network design, and verifies the effectiveness of the proposed framework through extensive experimental validation and comparisons to several baseline methods on benchmark datasets.
Multimodal Unsupervised Image-to-Image Translation
A Multimodal Unsupervised Image-to-image Translation (MUNIT) framework that assumes that the image representation can be decomposed into a content code that is domain-invariant, and a style code that captures domain-specific properties.
Diverse Image-to-Image Translation via Disentangled Representations
This work presents an approach based on disentangled representation for producing diverse outputs without paired training images, and proposes to embed images onto two spaces: a domain-invariant content space capturing shared information across domains and adomain-specific attribute space.