{"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/auto-encoded-supervision-for-perceptual-image","title":"Auto-Encoded Supervision for Perceptual Image Super-Resolution","arxiv_id":"2412.00124","date":"2024-11-28","proceeding":"CVPR 2025 1","authors":["MinKyu Lee","Sangeek Hyun","Woojin Jun","Jae-Pil Heo"],"abstract":"This work tackles the fidelity objective in the perceptual super-resolution~(SR). Specifically, we address the shortcomings of pixel-level $L_\\text{p}$ loss ($\\mathcal{L}_\\text{pix}$) in the GAN-based SR framework. Since $L_\\text{pix}$ is known to have a trade-off relationship against perceptual quality, prior methods often multiply a small scale factor or utilize low-pass filters. However, this work shows that these circumventions fail to address the fundamental factor that induces blurring. Accordingly, we focus on two points: 1) precisely discriminating the subcomponent of $L_\\text{pix}$ that contributes to blurring, and 2) only guiding based on the factor that is free from this trade-off relationship. We show that they can be achieved in a surprisingly simple manner, with an Auto-Encoder (AE) pretrained with $L_\\text{pix}$. Accordingly, we propose the Auto-Encoded Supervision for Optimal Penalization loss ($L_\\text{AESOP}$), a novel loss function that measures distance in the AE space, instead of the raw pixel space. Note that the AE space indicates the space after the decoder, not the bottleneck. By simply substituting $L_\\text{pix}$ with $L_\\text{AESOP}$, we can provide effective reconstruction guidance without compromising perceptual quality. Designed for simplicity, our method enables easy integration into existing SR frameworks. Experimental results verify that AESOP can lead to favorable results in the perceptual SR task.","url_abs":"https://arxiv.org/abs/2412.00124v2","url_pdf":"https://arxiv.org/pdf/2412.00124v2.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":"auto-encoded-supervision-for-perceptual-image","repo_url":"https://github.com/2minkyulee/aesop-auto-encoded-supervision-for-perceptual-image-super-resolution","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"image-super-resolution","task_name":"Image Super-Resolution"},{"task_slug":"super-resolution","task_name":"Super-Resolution"}],"methods":[{"method_slug":"ae","method_name":"AE"},{"method_slug":"focus","method_name":"Focus"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/image-super-resolution-on-bsd100-4x-upscaling","task":"Image Super-Resolution","dataset":"BSD100 - 4x upscaling","model":"AESOP","rank_in_archive_order":60,"of":71,"metrics":{"DISTS":"0.1072","LPIPS":"0.1385","PSNR":"25.93","SSIM":"0.6813"},"uses_additional_data":false},{"leaderboard":"/sota/image-super-resolution-on-div2k-val-4x","task":"Image Super-Resolution","dataset":"DIV2K val - 4x upscaling","model":"AESOP","rank_in_archive_order":1,"of":21,"metrics":{"DISTS":"0.0459","LPIPS":"0.0893","PSNR":"29.137","SSIM":"0.8023"},"uses_additional_data":false},{"leaderboard":"/sota/image-super-resolution-on-general-100-4x","task":"Image Super-Resolution","dataset":"General-100 - 4x upscaling","model":"AESOP","rank_in_archive_order":1,"of":1,"metrics":{"DISTS":"0.0762","LPIPS":"0.071","PSNR":"30.401","SSIM":"0.8328"},"uses_additional_data":false},{"leaderboard":"/sota/image-super-resolution-on-manga109-4x","task":"Image Super-Resolution","dataset":"Manga109 - 4x upscaling","model":"AESOP","rank_in_archive_order":42,"of":50,"metrics":{"DISTS":"0.0328","LPIPS":"0.0461","PSNR":"30.061","SSIM":"0.888"},"uses_additional_data":false},{"leaderboard":"/sota/image-super-resolution-on-set14-4x-upscaling","task":"Image Super-Resolution","dataset":"Set14 - 4x upscaling","model":"AESOP","rank_in_archive_order":95,"of":104,"metrics":{"DISTS":"0.0819","LPIPS":"0.1027","PSNR":"27.421","SSIM":"0.7438"},"uses_additional_data":false},{"leaderboard":"/sota/image-super-resolution-on-urban100-4x","task":"Image Super-Resolution","dataset":"Urban100 - 4x upscaling","model":"AESOP","rank_in_archive_order":41,"of":65,"metrics":{"DISTS":"0.0742","LPIPS":"0.0945","PSNR":"26.148","SSIM":"0.7884"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2412.00124","atlas_url":"https://app.syntology.ai/?focus=2412.00124","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.00124"}},"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/2minkyulee/aesop-auto-encoded-supervision-for-perceptual-image-super-resolution","reach":{"status":"ok"}}],"summary":{"ran_draft_wrong":2,"unverified":4},"by_repo_kind":{"official":{"samples":6,"ran":2,"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":6,"samples":[{"code_sha256_prefix":"2b7c2410e3f44ecb","entry":"get_local_weights","repo":"2minkyulee/aesop-auto-encoded-supervision-for-perceptual-image-super-resolution","repo_kind":"official","path":"AESOP/basicsr/losses/LDL_loss.py","file_url":"https://github.com/2minkyulee/aesop-auto-encoded-supervision-for-perceptual-image-super-resolution/blob/HEAD/AESOP/basicsr/losses/LDL_loss.py","link_basis":"plan_row","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"2b7c2410e3f44ecb"}},{"code_sha256_prefix":"c04a23de0531da4a","entry":"make_layer","repo":"2minkyulee/aesop-auto-encoded-supervision-for-perceptual-image-super-resolution","repo_kind":"official","path":"AESOP/basicsr/archs/rrdbnet_bsrgan_arch.py","file_url":"https://github.com/2minkyulee/aesop-auto-encoded-supervision-for-perceptual-image-super-resolution/blob/HEAD/AESOP/basicsr/archs/rrdbnet_bsrgan_arch.py","link_basis":"plan_row","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"c04a23de0531da4a"}},{"code_sha256_prefix":"9ea08fa86c19c513","entry":"get_refined_artifact_map","repo":"2minkyulee/aesop-auto-encoded-supervision-for-perceptual-image-super-resolution","repo_kind":"official","path":"AESOP/basicsr/losses/LDL_loss.py","file_url":"https://github.com/2minkyulee/aesop-auto-encoded-supervision-for-perceptual-image-super-resolution/blob/HEAD/AESOP/basicsr/losses/LDL_loss.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"9ea08fa86c19c513"}},{"code_sha256_prefix":"a648a03a952822c0","entry":"reduce_loss","repo":"2minkyulee/aesop-auto-encoded-supervision-for-perceptual-image-super-resolution","repo_kind":"official","path":"AESOP/basicsr/losses/loss_util.py","file_url":"https://github.com/2minkyulee/aesop-auto-encoded-supervision-for-perceptual-image-super-resolution/blob/HEAD/AESOP/basicsr/losses/loss_util.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"a648a03a952822c0"}},{"code_sha256_prefix":"1ba39317ea81871a","entry":"weight_reduce_loss","repo":"2minkyulee/aesop-auto-encoded-supervision-for-perceptual-image-super-resolution","repo_kind":"official","path":"AESOP/basicsr/losses/loss_util.py","file_url":"https://github.com/2minkyulee/aesop-auto-encoded-supervision-for-perceptual-image-super-resolution/blob/HEAD/AESOP/basicsr/losses/loss_util.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"1ba39317ea81871a"}},{"code_sha256_prefix":"cf63f8afc13f62a7","entry":"weighted_loss","repo":"2minkyulee/aesop-auto-encoded-supervision-for-perceptual-image-super-resolution","repo_kind":"official","path":"AESOP/basicsr/losses/loss_util.py","file_url":"https://github.com/2minkyulee/aesop-auto-encoded-supervision-for-perceptual-image-super-resolution/blob/HEAD/AESOP/basicsr/losses/loss_util.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"cf63f8afc13f62a7"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}