SemiNFT: Learning to Transfer Presets from Imitation to Appreciation via Hybrid-Sample Reinforcement Learning

• URL: http://arxiv.org/abs/2602.08582v1
• Date: Mon, 09 Feb 2026 12:20:33 GMT
• Title: SemiNFT: Learning to Transfer Presets from Imitation to Appreciation via Hybrid-Sample Reinforcement Learning
• Abstract summary: We propose a Diffusion Transformer-based retouching framework that mirrors the trajectory of human artistic training.<n>SemiNFT is first taught with paired triplets to acquire basic structural preservation and color mapping skills.<n>During the reinforcement learning stage, we design a hybrid online-offline reward mechanism that anchors aesthetic exploration with structural review.
• Score: 10.278887297409284
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Photorealistic color retouching plays a vital role in visual content creation, yet manual retouching remains inaccessible to non-experts due to its reliance on specialized expertise. Reference-based methods offer a promising alternative by transferring the preset color of a reference image to a source image. However, these approaches often operate as novice learners, performing global color mappings derived from pixel-level statistics, without a true understanding of semantic context or human aesthetics. To address this issue, we propose SemiNFT, a Diffusion Transformer (DiT)-based retouching framework that mirrors the trajectory of human artistic training: beginning with rigid imitation and evolving into intuitive creation. Specifically, SemiNFT is first taught with paired triplets to acquire basic structural preservation and color mapping skills, and then advanced to reinforcement learning (RL) on unpaired data to cultivate nuanced aesthetic perception. Crucially, during the RL stage, to prevent catastrophic forgetting of old skills, we design a hybrid online-offline reward mechanism that anchors aesthetic exploration with structural review. % experiments Extensive experiments show that SemiNFT not only outperforms state-of-the-art methods on standard preset transfer benchmarks but also demonstrates remarkable intelligence in zero-shot tasks, such as black-and-white photo colorization and cross-domain (anime-to-photo) preset transfer. These results confirm that SemiNFT transcends simple statistical matching and achieves a sophisticated level of aesthetic comprehension. Our project can be found at https://melanyyang.github.io/SemiNFT/.

Related papers

• Multimodal 3D LUT Generation via StatLUT with Statistical Features for Photorealistic Style Transfer [6.827125120104924]
  Photorealistic Style Transfer (PST) aims to transfer the color and tonal style of a reference to a content image.<n>Existing deep learning-based methods inherently suffer from semantic entanglement caused by pre-trained image encoders.<n>We propose StatLUT, an innovative multimodal framework for 3D LUT generation.
  arXiv  Detail & Related papers  (2026-07-09T08:23:04Z)
• Semi-LLIE: Semi-supervised Contrastive Learning with Mamba-based Low-light Image Enhancement [59.17372460692809]
  This work proposes a mean-teacher-based semi-supervised low-light enhancement (Semi-LLIE) framework that integrates the unpaired data into model training. We introduce a semantic-aware contrastive loss to faithfully transfer the illumination distribution, contributing to enhancing images with natural colors. We also propose novel perceptive loss based on the large-scale vision-language Recognize Anything Model (RAM) to help generate enhanced images with richer textual details.
  arXiv  Detail & Related papers  (2024-09-25T04:05:32Z)
• Enhance Image Classification via Inter-Class Image Mixup with Diffusion Model [80.61157097223058]
  A prevalent strategy to bolster image classification performance is through augmenting the training set with synthetic images generated by T2I models. In this study, we scrutinize the shortcomings of both current generative and conventional data augmentation techniques. We introduce an innovative inter-class data augmentation method known as Diff-Mix, which enriches the dataset by performing image translations between classes.
  arXiv  Detail & Related papers  (2024-03-28T17:23:45Z)
• Reducing Texture Bias of Deep Neural Networks via Edge Enhancing Diffusion [4.599829659954009]
  We study the texture bias of CNNs in semantic segmentation. We train CNNs on pre-processed images with less texture to reduce the texture bias. We observe strong texture-dependence of CNNs and moderate texture-dependence of transformers.
  arXiv  Detail & Related papers  (2024-02-14T19:10:40Z)
• Modeling Image Composition for Complex Scene Generation [77.10533862854706]
  We present a method that achieves state-of-the-art results on layout-to-image generation tasks. After compressing RGB images into patch tokens, we propose the Transformer with Focal Attention (TwFA) for exploring dependencies of object-to-object, object-to-patch and patch-to-patch.
  arXiv  Detail & Related papers  (2022-06-02T08:34:25Z)
• Towards a Unified Foundation Model: Jointly Pre-Training Transformers on Unpaired Images and Text [93.11954811297652]
  We design a unified transformer consisting of modality-specific tokenizers, a shared transformer encoder, and task-specific output heads. We employ the separately-trained BERT and ViT models as teachers and apply knowledge distillation to provide additional, accurate supervision signals. Experiments show that the resultant unified foundation transformer works surprisingly well on both the vision-only and text-only tasks.
  arXiv  Detail & Related papers  (2021-12-14T00:20:55Z)
• Deep Translation Prior: Test-time Training for Photorealistic Style Transfer [36.82737412912885]
  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.
  arXiv  Detail & Related papers  (2021-12-12T04:54:27Z)
• Palette: Image-to-Image Diffusion Models [50.268441533631176]
  We introduce Palette, a simple and general framework for image-to-image translation using conditional diffusion models. On four challenging image-to-image translation tasks, Palette outperforms strong GAN and regression baselines. We report several sample quality scores including FID, Inception Score, Classification Accuracy of a pre-trained ResNet-50, and Perceptual Distance against reference images.
  arXiv  Detail & Related papers  (2021-11-10T17:49:29Z)
• TUCaN: Progressively Teaching Colourisation to Capsules [13.50327471049997]
  We introduce a novel downsampling upsampling architecture named TUCaN (Tiny UCapsNet) We pose the problem as a per pixel colour classification task that identifies colours as a bin in a quantized space. To train the network, in contrast with the standard end to end learning method, we propose the progressive learning scheme to extract the context of objects.
  arXiv  Detail & Related papers  (2021-06-29T08:44:15Z)
• Supervised and Unsupervised Learning of Parameterized Color Enhancement [112.88623543850224]
  We tackle the problem of color enhancement as an image translation task using both supervised and unsupervised learning. We achieve state-of-the-art results compared to both supervised (paired data) and unsupervised (unpaired data) image enhancement methods on the MIT-Adobe FiveK benchmark. We show the generalization capability of our method, by applying it on photos from the early 20th century and to dark video frames.
  arXiv  Detail & Related papers  (2019-12-30T13:57:06Z)

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.