{"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/chain-of-zoom-extreme-super-resolution-via","title":"Chain-of-Zoom: Extreme Super-Resolution via Scale Autoregression and Preference Alignment","arxiv_id":"2505.18600","date":"2025-05-24","proceeding":null,"authors":["Bryan Sangwoo Kim","Jeongsol Kim","Jong Chul Ye"],"abstract":"Modern single-image super-resolution (SISR) models deliver photo-realistic results at the scale factors on which they are trained, but collapse when asked to magnify far beyond that regime. We address this scalability bottleneck with Chain-of-Zoom (CoZ), a model-agnostic framework that factorizes SISR into an autoregressive chain of intermediate scale-states with multi-scale-aware prompts. CoZ repeatedly re-uses a backbone SR model, decomposing the conditional probability into tractable sub-problems to achieve extreme resolutions without additional training. Because visual cues diminish at high magnifications, we augment each zoom step with multi-scale-aware text prompts generated by a vision-language model (VLM). The prompt extractor itself is fine-tuned using Generalized Reward Policy Optimization (GRPO) with a critic VLM, aligning text guidance towards human preference. Experiments show that a standard 4x diffusion SR model wrapped in CoZ attains beyond 256x enlargement with high perceptual quality and fidelity. Project Page: https://bryanswkim.github.io/chain-of-zoom/ .","url_abs":"https://arxiv.org/abs/2505.18600v2","url_pdf":"https://arxiv.org/pdf/2505.18600v2.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":"image-super-resolution","task_name":"Image Super-Resolution"},{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"super-resolution","task_name":"Super-Resolution"}],"methods":[{"method_slug":"diffusion","method_name":"Diffusion"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2505.18600","atlas_url":"https://app.syntology.ai/?focus=2505.18600","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.18600"}},"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":"deterministic:regex_extraction","url":"https://github.com/cswry/OSEDiff","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran":5,"ran_draft_wrong":5,"ran_fixture":2,"unverified":8},"by_repo_kind":{"found_in_text":{"samples":20,"ran":12,"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":"cd284aab598a07c2","entry":"GroupNormParam","repo":"cswry/OSEDiff","repo_kind":"found_in_text","path":"my_utils/vaehook.py","file_url":"https://github.com/cswry/OSEDiff/blob/HEAD/my_utils/vaehook.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"cd284aab598a07c2"}},{"code_sha256_prefix":"bc23635609cf5e46","entry":"attn_forward","repo":"cswry/OSEDiff","repo_kind":"found_in_text","path":"my_utils/vaehook.py","file_url":"https://github.com/cswry/OSEDiff/blob/HEAD/my_utils/vaehook.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"bc23635609cf5e46"}},{"code_sha256_prefix":"ad8c4ea29723e250","entry":"attn_forward_new","repo":"cswry/OSEDiff","repo_kind":"found_in_text","path":"my_utils/vaehook.py","file_url":"https://github.com/cswry/OSEDiff/blob/HEAD/my_utils/vaehook.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"ad8c4ea29723e250"}},{"code_sha256_prefix":"05623218f00496b1","entry":"clone_task_queue","repo":"cswry/OSEDiff","repo_kind":"found_in_text","path":"my_utils/vaehook.py","file_url":"https://github.com/cswry/OSEDiff/blob/HEAD/my_utils/vaehook.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"05623218f00496b1"}},{"code_sha256_prefix":"4f5087c964be075a","entry":"crop_valid_region","repo":"cswry/OSEDiff","repo_kind":"found_in_text","path":"my_utils/vaehook.py","file_url":"https://github.com/cswry/OSEDiff/blob/HEAD/my_utils/vaehook.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"4f5087c964be075a"}},{"code_sha256_prefix":"b9bb34c9f6fa3f19","entry":"custom_group_norm","repo":"cswry/OSEDiff","repo_kind":"found_in_text","path":"my_utils/vaehook.py","file_url":"https://github.com/cswry/OSEDiff/blob/HEAD/my_utils/vaehook.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"b9bb34c9f6fa3f19"}},{"code_sha256_prefix":"5b18dd6258dda3ac","entry":"get_cuda_device_string","repo":"cswry/OSEDiff","repo_kind":"found_in_text","path":"my_utils/vaehook.py","file_url":"https://github.com/cswry/OSEDiff/blob/HEAD/my_utils/vaehook.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"5b18dd6258dda3ac"}},{"code_sha256_prefix":"c0cb908a86960b3e","entry":"get_optimal_device","repo":"cswry/OSEDiff","repo_kind":"found_in_text","path":"my_utils/vaehook.py","file_url":"https://github.com/cswry/OSEDiff/blob/HEAD/my_utils/vaehook.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"c0cb908a86960b3e"}},{"code_sha256_prefix":"fdb5f42c95e7ce7c","entry":"get_optimal_device_name","repo":"cswry/OSEDiff","repo_kind":"found_in_text","path":"my_utils/vaehook.py","file_url":"https://github.com/cswry/OSEDiff/blob/HEAD/my_utils/vaehook.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"fdb5f42c95e7ce7c"}},{"code_sha256_prefix":"2c31ab46d2d7816d","entry":"get_var_mean","repo":"cswry/OSEDiff","repo_kind":"found_in_text","path":"my_utils/vaehook.py","file_url":"https://github.com/cswry/OSEDiff/blob/HEAD/my_utils/vaehook.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"2c31ab46d2d7816d"}},{"code_sha256_prefix":"d5f22536dca7a551","entry":"has_mps","repo":"cswry/OSEDiff","repo_kind":"found_in_text","path":"my_utils/vaehook.py","file_url":"https://github.com/cswry/OSEDiff/blob/HEAD/my_utils/vaehook.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"d5f22536dca7a551"}},{"code_sha256_prefix":"76a017e88938061d","entry":"inplace_nonlinearity","repo":"cswry/OSEDiff","repo_kind":"found_in_text","path":"my_utils/vaehook.py","file_url":"https://github.com/cswry/OSEDiff/blob/HEAD/my_utils/vaehook.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"76a017e88938061d"}},{"code_sha256_prefix":"12b0a428903ea66d","entry":"NansException","repo":"cswry/OSEDiff","repo_kind":"found_in_text","path":"my_utils/vaehook.py","file_url":"https://github.com/cswry/OSEDiff/blob/HEAD/my_utils/vaehook.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"12b0a428903ea66d"}},{"code_sha256_prefix":"a24a63fdf5977e44","entry":"VAEHook","repo":"cswry/OSEDiff","repo_kind":"found_in_text","path":"my_utils/vaehook.py","file_url":"https://github.com/cswry/OSEDiff/blob/HEAD/my_utils/vaehook.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"a24a63fdf5977e44"}},{"code_sha256_prefix":"8bae659fb7d40d76","entry":"attn2task","repo":"cswry/OSEDiff","repo_kind":"found_in_text","path":"my_utils/vaehook.py","file_url":"https://github.com/cswry/OSEDiff/blob/HEAD/my_utils/vaehook.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"8bae659fb7d40d76"}},{"code_sha256_prefix":"7a660644b945f53b","entry":"build_sampling","repo":"cswry/OSEDiff","repo_kind":"found_in_text","path":"my_utils/vaehook.py","file_url":"https://github.com/cswry/OSEDiff/blob/HEAD/my_utils/vaehook.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"7a660644b945f53b"}},{"code_sha256_prefix":"28e56cf67d286e05","entry":"build_task_queue","repo":"cswry/OSEDiff","repo_kind":"found_in_text","path":"my_utils/vaehook.py","file_url":"https://github.com/cswry/OSEDiff/blob/HEAD/my_utils/vaehook.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"28e56cf67d286e05"}},{"code_sha256_prefix":"6d2cccfb582558a7","entry":"resblock2task","repo":"cswry/OSEDiff","repo_kind":"found_in_text","path":"my_utils/vaehook.py","file_url":"https://github.com/cswry/OSEDiff/blob/HEAD/my_utils/vaehook.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"6d2cccfb582558a7"}},{"code_sha256_prefix":"3164631c0de24c4f","entry":"test_for_nans","repo":"cswry/OSEDiff","repo_kind":"found_in_text","path":"my_utils/vaehook.py","file_url":"https://github.com/cswry/OSEDiff/blob/HEAD/my_utils/vaehook.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"3164631c0de24c4f"}},{"code_sha256_prefix":"a97f72f307904874","entry":"xformer_attn_forward","repo":"cswry/OSEDiff","repo_kind":"found_in_text","path":"my_utils/vaehook.py","file_url":"https://github.com/cswry/OSEDiff/blob/HEAD/my_utils/vaehook.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"a97f72f307904874"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}