Style Transfer: From Stitching to Neural Networks

• URL: http://arxiv.org/abs/2409.00606v3
• Date: Tue, 12 Nov 2024 07:38:51 GMT
• Title: Style Transfer: From Stitching to Neural Networks
• Authors: Xinhe Xu, Zhuoer Wang, Yihan Zhang, Yizhou Liu, Zhaoyue Wang, Zhihao Xu, Muhan Zhao, Huaiying Luo,
• Abstract summary: This article compares two style transfer methods in image processing. The traditional method synthesizes new images by stitching together small patches from existing images, and a modern machine learning-based approach that uses a segmentation network to isolate foreground objects and apply style transfer solely to the background.
• Score: 5.539031975261105
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: This article compares two style transfer methods in image processing: the traditional method, which synthesizes new images by stitching together small patches from existing images, and a modern machine learning-based approach that uses a segmentation network to isolate foreground objects and apply style transfer solely to the background. The traditional method excels in creating artistic abstractions but can struggle with seamlessness, whereas the machine learning method preserves the integrity of foreground elements while enhancing the background, offering improved aesthetic quality and computational efficiency. Our study indicates that machine learning-based methods are more suited for real-world applications where detail preservation in foreground elements is essential.

Related papers

• SemanticStitch: Enhancing Image Coherence through Foreground-Aware Seam Carving [16.875629105210695]
  Traditional seam carving methods neglect semantic information, causing disruptions in foreground continuity.<n>We introduce SemanticStitch, a deep learning-based framework that incorporates semantic priors of foreground objects to preserve their integrity and enhance visual coherence.<n>Our approach includes a novel loss function that emphasizes the semantic integrity of salient objects, significantly improving stitching quality.
  arXiv  Detail & Related papers  (2025-11-15T08:05:29Z)
• DiffUHaul: A Training-Free Method for Object Dragging in Images [78.93531472479202]
  We propose a training-free method, dubbed DiffUHaul, for the object dragging task. We first apply attention masking in each denoising step to make the generation more disentangled across different objects. In the early denoising steps, we interpolate the attention features between source and target images to smoothly fuse new layouts with the original appearance.
  arXiv  Detail & Related papers  (2024-06-03T17:59:53Z)
• Regional Style and Color Transfer [1.6993555918144923]
  This paper presents a novel contribution to the field of regional style transfer. Existing methods often suffer from the drawback of applying style homogeneously across the entire image.
  arXiv  Detail & Related papers  (2024-04-22T05:07:02Z)
• Improved Object-Based Style Transfer with Single Deep Network [0.0]
  This research paper proposes a novel methodology for image-to-image style transfer on objects utilizing a single deep convolutional neural network. The primary objective is to enhance the visual appeal of objects in images by seamlessly transferring artistic styles while preserving the original object characteristics.
  arXiv  Detail & Related papers  (2024-04-15T05:00:40Z)
• Learning to Manipulate Artistic Images [27.803374400458402]
  We propose an arbitrary Style Image Manipulation Network (SIM-Net) Our method balances computational efficiency and high resolution to a certain extent. Both qualitative and quantitative experiments demonstrate the superiority of our method over state-of-the-art methods.
  arXiv  Detail & Related papers  (2024-01-25T06:34:49Z)
• 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)
• Learning Visual Representations for Transfer Learning by Suppressing Texture [38.901410057407766]
  In self-supervised learning, texture as a low-level cue may provide shortcuts that prevent the network from learning higher level representations. We propose to use classic methods based on anisotropic diffusion to augment training using images with suppressed texture. We empirically show that our method achieves state-of-the-art results on object detection and image classification.
  arXiv  Detail & Related papers  (2020-11-03T18:27:03Z)
• FeatMatch: Feature-Based Augmentation for Semi-Supervised Learning [64.32306537419498]
  We propose a novel learned feature-based refinement and augmentation method that produces a varied set of complex transformations. These transformations also use information from both within-class and across-class representations that we extract through clustering. We demonstrate that our method is comparable to current state of art for smaller datasets while being able to scale up to larger datasets.
  arXiv  Detail & Related papers  (2020-07-16T17:55:31Z)
• Region-adaptive Texture Enhancement for Detailed Person Image Synthesis [86.69934638569815]
  RATE-Net is a novel framework for synthesizing person images with sharp texture details. The proposed framework leverages an additional texture enhancing module to extract appearance information from the source image. Experiments conducted on DeepFashion benchmark dataset have demonstrated the superiority of our framework compared with existing networks.
  arXiv  Detail & Related papers  (2020-05-26T02:33:21Z)
• Scene Text Synthesis for Efficient and Effective Deep Network Training [62.631176120557136]
  We develop an innovative image synthesis technique that composes annotated training images by embedding foreground objects of interest into background images. The proposed technique consists of two key components that in principle boost the usefulness of the synthesized images in deep network training. Experiments over a number of public datasets demonstrate the effectiveness of our proposed image synthesis technique.
  arXiv  Detail & Related papers  (2019-01-26T10:15:24Z)

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.