Deep Translation Prior: Test-time Training for Photorealistic Style
Transfer
- URL: http://arxiv.org/abs/2112.06150v1
- Date: Sun, 12 Dec 2021 04:54:27 GMT
- Title: Deep Translation Prior: Test-time Training for Photorealistic Style
Transfer
- Authors: Sunwoo Kim, Soohyun Kim, Seungryong Kim
- Abstract summary: Recent techniques to solve photorealistic style transfer within deep convolutional neural networks (CNNs) generally require intensive training from large-scale datasets.
We propose a novel framework, dubbed Deep Translation Prior (DTP), to accomplish photorealistic style transfer through test-time training on given input image pair with untrained networks.
- Score: 36.82737412912885
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Recent techniques to solve photorealistic style transfer within deep
convolutional neural networks (CNNs) generally require intensive training from
large-scale datasets, thus having limited applicability and poor generalization
ability to unseen images or styles. To overcome this, we propose a novel
framework, dubbed Deep Translation Prior (DTP), to accomplish photorealistic
style transfer through test-time training on given input image pair with
untrained networks, which learns an image pair-specific translation prior and
thus yields better performance and generalization. Tailored for such test-time
training for style transfer, we present novel network architectures, with two
sub-modules of correspondence and generation modules, and loss functions
consisting of contrastive content, style, and cycle consistency losses. Our
framework does not require offline training phase for style transfer, which has
been one of the main challenges in existing methods, but the networks are to be
solely learned during test-time. Experimental results prove that our framework
has a better generalization ability to unseen image pairs and even outperforms
the state-of-the-art methods.
Related papers
- Adapt and Align to Improve Zero-Shot Sketch-Based Image Retrieval [85.39613457282107]
Cross-domain nature of sketch-based image retrieval is challenging.
We present an effective Adapt and Align'' approach to address the key challenges.
Inspired by recent advances in image-text foundation models (e.g., CLIP) on zero-shot scenarios, we explicitly align the learned image embedding with a more semantic text embedding to achieve the desired knowledge transfer from seen to unseen classes.
arXiv Detail & Related papers (2023-05-09T03:10:15Z) - A Unified Arbitrary Style Transfer Framework via Adaptive Contrastive
Learning [84.8813842101747]
Unified Contrastive Arbitrary Style Transfer (UCAST) is a novel style representation learning and transfer framework.
We present an adaptive contrastive learning scheme for style transfer by introducing an input-dependent temperature.
Our framework consists of three key components, i.e., a parallel contrastive learning scheme for style representation and style transfer, a domain enhancement module for effective learning of style distribution, and a generative network for style transfer.
arXiv Detail & Related papers (2023-03-09T04:35:00Z) - Controllable Style Transfer via Test-time Training of Implicit Neural
Representation [34.880651923701066]
We propose a controllable style transfer framework based on Implicit Neural Representation that pixel-wisely controls the stylized output via test-time training.
After being test-time trained once, thanks to the flexibility of the INR-based model, our framework can precisely control the stylized images in a pixel-wise manner and freely adjust image resolution without further optimization or training.
arXiv Detail & Related papers (2022-10-14T12:53:39Z) - Pretraining is All You Need for Image-to-Image Translation [59.43151345732397]
We propose to use pretraining to boost general image-to-image translation.
We show that the proposed pretraining-based image-to-image translation (PITI) is capable of synthesizing images of unprecedented realism and faithfulness.
arXiv Detail & Related papers (2022-05-25T17:58:26Z) - Deep Matching Prior: Test-Time Optimization for Dense Correspondence [37.492074298574664]
We show that an image pair-specific prior can be captured by solely optimizing the untrained matching networks on an input pair of images.
Experiments demonstrate that our framework, dubbed Deep Matching Prior (DMP), is competitive, or even outperforms, against the latest learning-based methods.
arXiv Detail & Related papers (2021-06-06T10:56:01Z) - StEP: Style-based Encoder Pre-training for Multi-modal Image Synthesis [68.3787368024951]
We propose a novel approach for multi-modal Image-to-image (I2I) translation.
We learn a latent embedding, jointly with the generator, that models the variability of the output domain.
Specifically, we pre-train a generic style encoder using a novel proxy task to learn an embedding of images, from arbitrary domains, into a low-dimensional style latent space.
arXiv Detail & Related papers (2021-04-14T19:58:24Z) - Online Exemplar Fine-Tuning for Image-to-Image Translation [32.556050882376965]
Existing techniques to solve exemplar-based image-to-image translation within deep convolutional neural networks (CNNs) generally require a training phase to optimize the network parameters.
We propose a novel framework, for the first time, to solve exemplar-based translation through an online optimization given an input image pair.
Our framework does not require the off-line training phase, which has been the main challenge of existing methods, but the pre-trained networks to enable optimization in online.
arXiv Detail & Related papers (2020-11-18T15:13:16Z) - Adversarially-Trained Deep Nets Transfer Better: Illustration on Image
Classification [53.735029033681435]
Transfer learning is a powerful methodology for adapting pre-trained deep neural networks on image recognition tasks to new domains.
In this work, we demonstrate that adversarially-trained models transfer better than non-adversarially-trained models.
arXiv Detail & Related papers (2020-07-11T22:48:42Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.