Personalized Image Filter: Mastering Your Photographic Style

• URL: http://arxiv.org/abs/2510.16791v1
• Date: Sun, 19 Oct 2025 11:03:21 GMT
• Title: Personalized Image Filter: Mastering Your Photographic Style
• Authors: Chengxuan Zhu, Shuchen Weng, Jiacong Fang, Peixuan Zhang, Si Li, Chao Xu, Boxin Shi,
• Abstract summary: generative prior enables PIF to learn the average appearance of photographic concepts.<n>PIF shows outstanding performance in extracting and transferring various kinds of photographic style.
• Score: 57.83973633106558
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Photographic style, as a composition of certain photographic concepts, is the charm behind renowned photographers. But learning and transferring photographic style need a profound understanding of how the photo is edited from the unknown original appearance. Previous works either fail to learn meaningful photographic concepts from reference images, or cannot preserve the content of the content image. To tackle these issues, we proposed a Personalized Image Filter (PIF). Based on a pretrained text-to-image diffusion model, the generative prior enables PIF to learn the average appearance of photographic concepts, as well as how to adjust them according to text prompts. PIF then learns the photographic style of reference images with the textual inversion technique, by optimizing the prompts for the photographic concepts. PIF shows outstanding performance in extracting and transferring various kinds of photographic style. Project page: https://pif.pages.dev/

Related papers

• PhotoDoodle: Learning Artistic Image Editing from Few-Shot Pairwise Data [24.08203111413198]
  Photo doodling is challenging because the inserted elements must appear seamlessly integrated with the background.<n>The proposed method, PhotoDoodle, employs a two-stage training strategy.<n>To enhance consistency in the generated results, we introduce a positional encoding reuse mechanism.
  arXiv  Detail & Related papers  (2025-02-20T09:35:38Z)
• Decoupled Textual Embeddings for Customized Image Generation [62.98933630971543]
  Customized text-to-image generation aims to learn user-specified concepts with a few images. Existing methods usually suffer from overfitting issues and entangle the subject-unrelated information with the learned concept. We propose the DETEX, a novel approach that learns the disentangled concept embedding for flexible customized text-to-image generation.
  arXiv  Detail & Related papers  (2023-12-19T03:32:10Z)
• Photoswap: Personalized Subject Swapping in Images [56.2650908740358]
  Photoswap learns the visual concept of the subject from reference images and swaps it into the target image using pre-trained diffusion models. Photoswap significantly outperforms baseline methods in human ratings across subject swapping, background preservation, and overall quality.
  arXiv  Detail & Related papers  (2023-05-29T17:56:13Z)
• Text-Guided Scene Sketch-to-Photo Synthesis [5.431298869139175]
  We propose a method for scene-level sketch-to-photo synthesis with text guidance. To train our model, we use self-supervised learning from a set of photographs. Experiments show that the proposed method translates original sketch images that are not extracted from color images into photos with compelling visual quality.
  arXiv  Detail & Related papers  (2023-02-14T08:13:36Z)
• Zero-shot Image-to-Image Translation [57.46189236379433]
  We propose pix2pix-zero, an image-to-image translation method that can preserve the original image without manual prompting. We propose cross-attention guidance, which aims to retain the cross-attention maps of the input image throughout the diffusion process. Our method does not need additional training for these edits and can directly use the existing text-to-image diffusion model.
  arXiv  Detail & Related papers  (2023-02-06T18:59:51Z)
• Aesthetic Language Guidance Generation of Images Using Attribute Comparison [68.01313297926109]
  The improvement of intelligent equipments and algorithms cannot replace human subjective photography technology. We divide aesthetic language guidance of image (ALG) into ALG-T and ALG-I. Both ALG-T and ALG-I conduct aesthetic language guidance respectively for the two types of input images.
  arXiv  Detail & Related papers  (2022-08-09T12:35:23Z)
• Filter Style Transfer between Photos [11.796188165729342]
  Filter Style Transfer (FST) is first style transfer method that can transfer custom filter effects between FHD image under 2ms on a mobile device without any textual context loss.
  arXiv  Detail & Related papers  (2020-07-15T18:09:35Z)
• Towards Photo-Realistic Virtual Try-On by Adaptively Generating$\leftrightarrow$Preserving Image Content [85.24260811659094]
  We propose a novel visual try-on network, namely Adaptive Content Generating and Preserving Network (ACGPN) ACGPN first predicts semantic layout of the reference image that will be changed after try-on. Second, a clothes warping module warps clothing images according to the generated semantic layout. Third, an inpainting module for content fusion integrates all information (e.g. reference image, semantic layout, warped clothes) to adaptively produce each semantic part of human body.
  arXiv  Detail & Related papers  (2020-03-12T15:55:39Z)

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.