Multiscale Sliced Wasserstein Distances as Perceptual Color Difference Measures

• URL: http://arxiv.org/abs/2407.10181v1
• Date: Sun, 14 Jul 2024 12:48:16 GMT
• Title: Multiscale Sliced Wasserstein Distances as Perceptual Color Difference Measures
• Authors: Jiaqi He, Zhihua Wang, Leon Wang, Tsein-I Liu, Yuming Fang, Qilin Sun, Kede Ma,
• Abstract summary: We describe a perceptual CD measure based on the multiscale sliced Wasserstein distance. Experimental results indicate that our CD measure performs favorably in assessing CDs in photographic images. Our measure functions as a metric in the mathematical sense, and show its promise as a loss function for image and video color transfer tasks.
• Score: 34.8728594246521
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Contemporary color difference (CD) measures for photographic images typically operate by comparing co-located pixels, patches in a ``perceptually uniform'' color space, or features in a learned latent space. Consequently, these measures inadequately capture the human color perception of misaligned image pairs, which are prevalent in digital photography (e.g., the same scene captured by different smartphones). In this paper, we describe a perceptual CD measure based on the multiscale sliced Wasserstein distance, which facilitates efficient comparisons between non-local patches of similar color and structure. This aligns with the modern understanding of color perception, where color and structure are inextricably interdependent as a unitary process of perceptual organization. Meanwhile, our method is easy to implement and training-free. Experimental results indicate that our CD measure performs favorably in assessing CDs in photographic images, and consistently surpasses competing models in the presence of image misalignment. Additionally, we empirically verify that our measure functions as a metric in the mathematical sense, and show its promise as a loss function for image and video color transfer tasks. The code is available at https://github.com/real-hjq/MS-SWD.

Related papers

• Control Color: Multimodal Diffusion-based Interactive Image Colorization [81.68817300796644]
  Control Color (Ctrl Color) is a multi-modal colorization method that leverages the pre-trained Stable Diffusion (SD) model. We present an effective way to encode user strokes to enable precise local color manipulation. We also introduce a novel module based on self-attention and a content-guided deformable autoencoder to address the long-standing issues of color overflow and inaccurate coloring.
  arXiv  Detail & Related papers  (2024-02-16T17:51:13Z)
• SPDGAN: A Generative Adversarial Network based on SPD Manifold Learning for Automatic Image Colorization [1.220743263007369]
  We propose a fully automatic colorization approach based on Symmetric Positive Definite (SPD) Manifold Learning with a generative adversarial network (SPDGAN) Our model establishes an adversarial game between two discriminators and a generator. Its goal is to generate fake colorized images without losing color information across layers through residual connections.
  arXiv  Detail & Related papers  (2023-12-21T00:52:01Z)
• Learning a Deep Color Difference Metric for Photographic Images [36.66506502182684]
  We learn a deep CD metric for photographic images with four desirable properties. It computes accurate CDs between photographic images, differing mainly in color appearances. We show that all these properties can be satisfied at once by learning a multi-scale autoregressive normalizing flow for feature transform.
  arXiv  Detail & Related papers  (2023-03-27T07:54:09Z)
• Name Your Colour For the Task: Artificially Discover Colour Naming via Colour Quantisation Transformer [62.75343115345667]
  We propose a novel colour quantisation transformer, CQFormer, that quantises colour space while maintaining machine recognition on the quantised images. We observe the consistent evolution pattern between our artificial colour system and basic colour terms across human languages. Our colour quantisation method also offers an efficient quantisation method that effectively compresses the image storage.
  arXiv  Detail & Related papers  (2022-12-07T03:39:18Z)
• Deep Metric Color Embeddings for Splicing Localization in Severely Degraded Images [10.091921099426294]
  We explore an alternative approach to splicing detection, which is potentially better suited for images in-the-wild. We learn a deep metric space that is on one hand sensitive to illumination color and camera white-point estimation, but on the other hand insensitive to variations in object color. In our evaluation, we show that the proposed embedding space outperforms the state of the art on images that have been subject to strong compression and downsampling.
  arXiv  Detail & Related papers  (2022-06-21T21:28:40Z)
• Measuring Perceptual Color Differences of Smartphone Photographs [55.9434603885868]
  We put together the largest image dataset for perceptual CD assessment. We make one of the first attempts to construct an end-to-end learnable CD formula based on a lightweight neural network.
  arXiv  Detail & Related papers  (2022-05-26T16:57:04Z)
• Detecting Recolored Image by Spatial Correlation [60.08643417333974]
  Image recoloring is an emerging editing technique that can manipulate the color values of an image to give it a new style. In this paper, we explore a solution from the perspective of the spatial correlation, which exhibits the generic detection capability for both conventional and deep learning-based recoloring. Our method achieves the state-of-the-art detection accuracy on multiple benchmark datasets and exhibits well generalization for unknown types of recoloring methods.
  arXiv  Detail & Related papers  (2022-04-23T01:54:06Z)
• Colour alignment for relative colour constancy via non-standard references [11.92389176996629]
  Relative colour constancy is an essential requirement for many scientific imaging applications. We propose a colour alignment model that considers the camera image formation as a black-box. It formulates colour alignment as a three-step process: camera response calibration, response linearisation, and colour matching.
  arXiv  Detail & Related papers  (2021-12-30T15:58:55Z)
• Learning to Structure an Image with Few Colors [59.34619548026885]
  We propose a color quantization network, ColorCNN, which learns to structure the images from the classification loss in an end-to-end manner. With only a 1-bit color space (i.e., two colors), the proposed network achieves 82.1% top-1 accuracy on the CIFAR10 dataset. For applications, when encoded with PNG, the proposed color quantization shows superiority over other image compression methods in the extremely low bit-rate regime.
  arXiv  Detail & Related papers  (2020-03-17T17:56:15Z)

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.