Spatial-Separated Curve Rendering Network for Efficient and High-Resolution Image Harmonization

• URL: http://arxiv.org/abs/2109.05750v2
• Date: Tue, 14 Sep 2021 08:02:51 GMT
• Title: Spatial-Separated Curve Rendering Network for Efficient and High-Resolution Image Harmonization
• Authors: Jingtang Liang, Xiaodong Cun and Chi-Man Pun
• Abstract summary: We propose a novel spatial-separated curve rendering network (S$2$CRNet) for efficient and high-resolution image harmonization. The proposed method reduces more than 90% parameters compared with previous methods. Our method can work smoothly on higher resolution images in real-time which is more than 10$times$ faster than the existing methods.
• Score: 59.19214040221055
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Image harmonization aims to modify the color of the composited region with respect to the specific background. Previous works model this task as a pixel-wise image-to-image translation using UNet family structures. However, the model size and computational cost limit the performability of their models on edge devices and higher-resolution images. To this end, we propose a novel spatial-separated curve rendering network (S$^2$CRNet) for efficient and high-resolution image harmonization for the first time. In S$^2$CRNet, we firstly extract the spatial-separated embeddings from the thumbnails of the masked foreground and background individually. Then, we design a curve rendering module (CRM), which learns and combines the spatial-specific knowledge using linear layers to generate the parameters of the pixel-wise curve mapping in the foreground region. Finally, we directly render the original high-resolution images using the learned color curve. Besides, we also make two extensions of the proposed framework via the Cascaded-CRM and Semantic-CRM for cascaded refinement and semantic guidance, respectively. Experiments show that the proposed method reduces more than 90% parameters compared with previous methods but still achieves the state-of-the-art performance on both synthesized iHarmony4 and real-world DIH test set. Moreover, our method can work smoothly on higher resolution images in real-time which is more than 10$\times$ faster than the existing methods. The code and pre-trained models will be made available and released at https://github.com/stefanLeong/S2CRNet.

Related papers

• Multi-Head Attention Residual Unfolded Network for Model-Based Pansharpening [2.874893537471256]
  Unfolding fusion methods integrate the powerful representation capabilities of deep learning with the robustness of model-based approaches. In this paper, we propose a model-based deep unfolded method for satellite image fusion. Experimental results on PRISMA, Quickbird, and WorldView2 datasets demonstrate the superior performance of our method.
  arXiv  Detail & Related papers  (2024-09-04T13:05:00Z)
• Beyond Learned Metadata-based Raw Image Reconstruction [86.1667769209103]
  Raw images have distinct advantages over sRGB images, e.g., linearity and fine-grained quantization levels. They are not widely adopted by general users due to their substantial storage requirements. We propose a novel framework that learns a compact representation in the latent space, serving as metadata.
  arXiv  Detail & Related papers  (2023-06-21T06:59:07Z)
• Multiscale Representation for Real-Time Anti-Aliasing Neural Rendering [84.37776381343662]
  Mip-NeRF proposes a multiscale representation as a conical frustum to encode scale information. We propose mip voxel grids (Mip-VoG), an explicit multiscale representation for real-time anti-aliasing rendering. Our approach is the first to offer multiscale training and real-time anti-aliasing rendering simultaneously.
  arXiv  Detail & Related papers  (2023-04-20T04:05:22Z)
• CoordFill: Efficient High-Resolution Image Inpainting via Parameterized Coordinate Querying [52.91778151771145]
  In this paper, we try to break the limitations for the first time thanks to the recent development of continuous implicit representation. Experiments show that the proposed method achieves real-time performance on the 2048$times$2048 images using a single GTX 2080 Ti GPU.
  arXiv  Detail & Related papers  (2023-03-15T11:13:51Z)
• Dense Pixel-to-Pixel Harmonization via Continuous Image Representation [22.984119094424056]
  We propose a novel image Harmonization method based on Implicit neural Networks (HINet) Inspired by the Retinex theory, we decouple the harmonizations into two parts to respectively capture the content and environment of composite images. Extensive experiments have demonstrated the effectiveness of our method compared with state-of-the-art methods.
  arXiv  Detail & Related papers  (2023-03-03T02:52:28Z)
• FRIH: Fine-grained Region-aware Image Harmonization [49.420765789360836]
  We propose a novel global-local two stages framework for Fine-grained Region-aware Image Harmonization (FRIH) Our algorithm achieves the best performance on iHarmony4 dataset (PSNR is 38.19 dB) with a lightweight model.
  arXiv  Detail & Related papers  (2022-05-13T04:50:26Z)
• SCSNet: An Efficient Paradigm for Learning Simultaneously Image Colorization and Super-Resolution [39.77987463287673]
  We present an efficient paradigm to perform Simultaneously Image Colorization and Super-resolution (SCS) The proposed method consists of two parts: colorization branch for learning color information that employs the proposed plug-and-play emphPyramid Valve Cross Attention (PVCAttn) module. Our SCSNet supports both automatic and referential modes that is more flexible for practical application.
  arXiv  Detail & Related papers  (2022-01-12T08:59:12Z)
• OSLO: On-the-Sphere Learning for Omnidirectional images and its application to 360-degree image compression [59.58879331876508]
  We study the learning of representation models for omnidirectional images and propose to use the properties of HEALPix uniform sampling of the sphere to redefine the mathematical tools used in deep learning models for omnidirectional images. Our proposed on-the-sphere solution leads to a better compression gain that can save 13.7% of the bit rate compared to similar learned models applied to equirectangular images.
  arXiv  Detail & Related papers  (2021-07-19T22:14:30Z)

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.