{"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/fidelity-controllable-extreme-image","title":"Fidelity-Controllable Extreme Image Compression with Generative Adversarial Networks","arxiv_id":"2008.10314","date":"2020-08-24","proceeding":null,"authors":["Shoma Iwai","Tomo Miyazaki","Yoshihiro Sugaya","Shinichiro Omachi"],"abstract":"We propose a GAN-based image compression method working at extremely low bitrates below 0.1bpp. Most existing learned image compression methods suffer from blur at extremely low bitrates. Although GAN can help to reconstruct sharp images, there are two drawbacks. First, GAN makes training unstable. Second, the reconstructions often contain unpleasing noise or artifacts. To address both of the drawbacks, our method adopts two-stage training and network interpolation. The two-stage training is effective to stabilize the training. Moreover, the network interpolation utilizes the models in both stages and reduces undesirable noise and artifacts, while maintaining important edges. Hence, we can control the trade-off between perceptual quality and fidelity without re-training models. The experimental results show that our model can reconstruct high quality images. Furthermore, our user study confirms that our reconstructions are preferable to state-of-the-art GAN-based image compression model. The code will be available.","url_abs":"https://arxiv.org/abs/2008.10314v1","url_pdf":"https://arxiv.org/pdf/2008.10314v1.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":"fidelity-controllable-extreme-image","repo_url":"https://github.com/iwa-shi/fidelity_controllable_compression","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"image-compression","task_name":"Image Compression"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2008.10314","atlas_url":"https://app.syntology.ai/?focus=2008.10314","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2008.10314"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/iwa-shi/fidelity_controllable_compression","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":4},"by_repo_kind":{"official":{"samples":4,"ran":0,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"ffc5d056ef919bce","entry":"decode_header","repo":"iwa-shi/fidelity_controllable_compression","repo_kind":"official","path":"codec.py","file_url":"https://github.com/iwa-shi/fidelity_controllable_compression/blob/HEAD/codec.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"ffc5d056ef919bce"}},{"code_sha256_prefix":"adbded77b7172588","entry":"encode_header","repo":"iwa-shi/fidelity_controllable_compression","repo_kind":"official","path":"codec.py","file_url":"https://github.com/iwa-shi/fidelity_controllable_compression/blob/HEAD/codec.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"adbded77b7172588"}},{"code_sha256_prefix":"e4975b641d631917","entry":"load_byte_strings","repo":"iwa-shi/fidelity_controllable_compression","repo_kind":"official","path":"codec.py","file_url":"https://github.com/iwa-shi/fidelity_controllable_compression/blob/HEAD/codec.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"e4975b641d631917"}},{"code_sha256_prefix":"1f0fda156f2efc67","entry":"normalize_cdf","repo":"iwa-shi/fidelity_controllable_compression","repo_kind":"official","path":"rangecoder.py","file_url":"https://github.com/iwa-shi/fidelity_controllable_compression/blob/HEAD/rangecoder.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"1f0fda156f2efc67"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}