{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/implicit-dual-domain-convolutional-network","title":"Implicit Dual-domain Convolutional Network for Robust Color Image Compression Artifact Reduction","arxiv_id":"1810.08042","date":"2018-10-18","proceeding":null,"authors":["Bolun Zheng","Yaowu Chen","Xiang Tian","Fan Zhou","Xuesong Liu"],"abstract":"Several dual-domain convolutional neural network-based methods show outstanding performance in reducing image compression artifacts. However, they suffer from handling color images because the compression processes for gray-scale and color images are completely different. Moreover, these methods train a specific model for each compression quality and require multiple models to achieve different compression qualities. To address these problems, we proposed an implicit dual-domain convolutional network (IDCN) with the pixel position labeling map and the quantization tables as inputs. Specifically, we proposed an extractor-corrector framework-based dual-domain correction unit (DCU) as the basic component to formulate the IDCN. A dense block was introduced to improve the performance of extractor in DRU. The implicit dual-domain translation allows the IDCN to handle color images with the discrete cosine transform (DCT)-domain priors. A flexible version of IDCN (IDCN-f) was developed to handle a wide range of compression qualities. Experiments for both objective and subjective evaluations on benchmark datasets show that IDCN is superior to the state-of-the-art methods and IDCN-f exhibits excellent abilities to handle a wide range of compression qualities with little performance sacrifice and demonstrates great potential for practical applications.","url_abs":"https://arxiv.org/abs/1810.08042v3","url_pdf":"https://arxiv.org/pdf/1810.08042v3.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[],"tasks":[{"task_slug":"color-image-compression-artifact-reduction","task_name":"Color Image Compression Artifact Reduction"},{"task_slug":"image-compression","task_name":"Image Compression"},{"task_slug":"image-compression-artifact-reduction","task_name":"Image Compression Artifact Reduction"},{"task_slug":"jpeg-artifact-correction","task_name":"JPEG Artifact Correction"},{"task_slug":"quantization","task_name":"Quantization"},{"task_slug":"translation","task_name":"Translation"}],"methods":[{"method_slug":"batch-normalization","method_name":"Batch Normalization"},{"method_slug":"concatenated-skip-connection","method_name":"Concatenated Skip Connection"},{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"dense-block","method_name":"Dense Block"},{"method_slug":"discrete-cosine-transform","method_name":"Discrete Cosine Transform"},{"method_slug":"relu","method_name":"ReLU"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/jpeg-artifact-correction-on-icb-quality-10","task":"JPEG Artifact Correction","dataset":"ICB (Quality 10 Color)","model":"IDCN","rank_in_archive_order":3,"of":6,"metrics":{"PSNR":"31.71","PSNR-B":"32.02","SSIM":"0.809"},"uses_additional_data":false},{"leaderboard":"/sota/jpeg-artifact-correction-on-icb-quality-10-1","task":"JPEG Artifact Correction","dataset":"ICB (Quality 10 Grayscale)","model":"IDCN","rank_in_archive_order":4,"of":5,"metrics":{"PSNR":"32.50","PSNR-B":"32.42","SSIM":"0.826"},"uses_additional_data":false},{"leaderboard":"/sota/jpeg-artifact-correction-on-icb-quality-20","task":"JPEG Artifact Correction","dataset":"ICB (Quality 20 Color)","model":"IDCN","rank_in_archive_order":3,"of":6,"metrics":{"PSNR":"33.99","PSNR-B":"34.37","SSIM":"0.838"},"uses_additional_data":false},{"leaderboard":"/sota/jpeg-artifact-correction-on-icb-quality-20-1","task":"JPEG Artifact Correction","dataset":"ICB (Quality 20 Grayscale)","model":"IDCN","rank_in_archive_order":5,"of":5,"metrics":{"PSNR":"34.30","PSNR-B":"34.18","SSIM":"0.851"},"uses_additional_data":false},{"leaderboard":"/sota/jpeg-artifact-correction-on-live1-quality-10","task":"JPEG Artifact Correction","dataset":"LIVE1 (Quality 10 Color)","model":"IDCN","rank_in_archive_order":4,"of":9,"metrics":{"PSNR":"27.63","PSNR-B":"27.63","SSIM":"0.816"},"uses_additional_data":false},{"leaderboard":"/sota/jpeg-artifact-correction-on-live1-quality-20","task":"JPEG Artifact Correction","dataset":"LIVE1 (Quality 20 Color)","model":"IDCN","rank_in_archive_order":3,"of":9,"metrics":{"PSNR":"30.04","PSNR-B":"30.01","SSIM":"0.882"},"uses_additional_data":false},{"leaderboard":"/sota/jpeg-artifact-correction-on-live1-quality-20-1","task":"JPEG Artifact Correction","dataset":"LIVE1 (Quality 20 Grayscale)","model":"IDCN","rank_in_archive_order":4,"of":12,"metrics":{"PSNR":"32.09","PSNR-B":"32.00","SSIM":"0.9006"},"uses_additional_data":false},{"leaderboard":"/sota/jpeg-artifact-correction-on-live1-quality-10-1","task":"JPEG Artifact Correction","dataset":"Live1 (Quality 10 Grayscale)","model":"IDCN","rank_in_archive_order":3,"of":13,"metrics":{"PSNR":"29.71","PSNR-B":"29.66","SSIM":"0.838"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1810.08042","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}