{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/icolorit-towards-propagating-local-hint-to","title":"iColoriT: Towards Propagating Local Hint to the Right Region in Interactive Colorization by Leveraging Vision Transformer","arxiv_id":"2207.06831","date":"2022-07-14","proceeding":null,"authors":["Jooyeol Yun","Sanghyeon Lee","Minho Park","Jaegul Choo"],"abstract":"Point-interactive image colorization aims to colorize grayscale images when a user provides the colors for specific locations. It is essential for point-interactive colorization methods to appropriately propagate user-provided colors (i.e., user hints) in the entire image to obtain a reasonably colorized image with minimal user effort. However, existing approaches often produce partially colorized results due to the inefficient design of stacking convolutional layers to propagate hints to distant relevant regions. To address this problem, we present iColoriT, a novel point-interactive colorization Vision Transformer capable of propagating user hints to relevant regions, leveraging the global receptive field of Transformers. The self-attention mechanism of Transformers enables iColoriT to selectively colorize relevant regions with only a few local hints. Our approach colorizes images in real-time by utilizing pixel shuffling, an efficient upsampling technique that replaces the decoder architecture. Also, in order to mitigate the artifacts caused by pixel shuffling with large upsampling ratios, we present the local stabilizing layer. Extensive quantitative and qualitative results demonstrate that our approach highly outperforms existing methods for point-interactive colorization, producing accurately colorized images with a user's minimal effort. Official codes are available at https://pmh9960.github.io/research/iColoriT","url_abs":"https://arxiv.org/abs/2207.06831v4","url_pdf":"https://arxiv.org/pdf/2207.06831v4.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":[{"paper_slug":"icolorit-towards-propagating-local-hint-to","repo_url":"https://github.com/pmh9960/iColoriT","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"colorization","task_name":"Colorization"},{"task_slug":"decoder","task_name":"Decoder"},{"task_slug":"image-colorization","task_name":"Image Colorization"},{"task_slug":"point-interactive-image-colorization","task_name":"Point-interactive Image Colorization"}],"methods":[{"method_slug":"absolute-position-encodings","method_name":"Absolute Position Encodings"},{"method_slug":"adam","method_name":"Adam"},{"method_slug":"bpe","method_name":"BPE"},{"method_slug":"colorization","method_name":"Colorization"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"label-smoothing","method_name":"Label Smoothing"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"position-wise-feed-forward-layer","method_name":"Position-Wise Feed-Forward Layer"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"transformer","method_name":"Transformer"},{"method_slug":"vision-transformer","method_name":"Vision Transformer"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/point-interactive-image-colorization-on-cub","task":"Point-interactive Image Colorization","dataset":"CUB-200-2011","model":"iColoriT","rank_in_archive_order":1,"of":7,"metrics":{"PSNR@1":"27.986","PSNR@10":"30.595","PSNR@100":"33.543"},"uses_additional_data":false},{"leaderboard":"/sota/point-interactive-image-colorization-on-cub","task":"Point-interactive Image Colorization","dataset":"CUB-200-2011","model":"InstColor","rank_in_archive_order":3,"of":7,"metrics":{"PSNR@1":"27.69","PSNR@10":"29.45","PSNR@100":"31.45"},"uses_additional_data":false},{"leaderboard":"/sota/point-interactive-image-colorization-on-cub","task":"Point-interactive Image Colorization","dataset":"CUB-200-2011","model":"iDeepColor","rank_in_archive_order":5,"of":7,"metrics":{"PSNR@1":"27.45","PSNR@10":"29.32","PSNR@100":"31.57"},"uses_additional_data":false},{"leaderboard":"/sota/point-interactive-image-colorization-on-cub","task":"Point-interactive Image Colorization","dataset":"CUB-200-2011","model":"SWF","rank_in_archive_order":7,"of":7,"metrics":{"PSNR@1":"23.547","PSNR@10":"25.097","PSNR@100":"27.623"},"uses_additional_data":false},{"leaderboard":"/sota/point-interactive-image-colorization-on","task":"Point-interactive Image Colorization","dataset":"ImageNet ctest10k","model":"iColoriT","rank_in_archive_order":1,"of":4,"metrics":{"PSNR@1":"27.474","PSNR@10":"30.626","PSNR@100":"33.787"},"uses_additional_data":false},{"leaderboard":"/sota/point-interactive-image-colorization-on-1","task":"Point-interactive Image Colorization","dataset":"Oxford 102 Flowers","model":"iColoriT","rank_in_archive_order":1,"of":7,"metrics":{"PSNR@1":"22.925","PSNR@10":"27.37","PSNR@100":"30.731"},"uses_additional_data":false},{"leaderboard":"/sota/point-interactive-image-colorization-on-1","task":"Point-interactive Image Colorization","dataset":"Oxford 102 Flowers","model":"iDeepColor","rank_in_archive_order":4,"of":7,"metrics":{"PSNR@1":"22.72","PSNR@10":"25.13","PSNR@100":"27.826"},"uses_additional_data":false},{"leaderboard":"/sota/point-interactive-image-colorization-on-1","task":"Point-interactive Image Colorization","dataset":"Oxford 102 Flowers","model":"SWF","rank_in_archive_order":6,"of":7,"metrics":{"PSNR@1":"18.452","PSNR@10":"19.445","PSNR@100":"22.362"},"uses_additional_data":false},{"leaderboard":"/sota/point-interactive-image-colorization-on-1","task":"Point-interactive Image Colorization","dataset":"Oxford 102 Flowers","model":"InstColor","rank_in_archive_order":7,"of":7,"metrics":{"PSNR@1":"22.97","PSNR@100":"27.35"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers","held":null,"reason":"arxiv_id_not_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"by_repo":[{"repo":"pmh9960/iColoriT","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0}],"by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"4a39ca8323dbe6901fb119344627fa900550bda20e870f75d81396c9bb8b42f8","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}