{"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/diffusion-based-extreme-image-compression","title":"RDEIC: Accelerating Diffusion-Based Extreme Image Compression with Relay Residual Diffusion","arxiv_id":"2410.02640","date":"2024-10-03","proceeding":null,"authors":["Zhiyuan Li","Yanhui Zhou","Hao Wei","Chenyang Ge","Ajmal Mian"],"abstract":"Diffusion-based extreme image compression methods have achieved impressive performance at extremely low bitrates. However, constrained by the iterative denoising process that starts from pure noise, these methods are limited in both fidelity and efficiency. To address these two issues, we present Relay Residual Diffusion Extreme Image Compression (RDEIC), which leverages compressed feature initialization and residual diffusion. Specifically, we first use the compressed latent features of the image with added noise, instead of pure noise, as the starting point to eliminate the unnecessary initial stages of the denoising process. Second, we directly derive a novel residual diffusion equation from Stable Diffusion's original diffusion equation that reconstructs the raw image by iteratively removing the added noise and the residual between the compressed and target latent features. In this way, we effectively combine the efficiency of residual diffusion with the powerful generative capability of Stable Diffusion. Third, we propose a fixed-step fine-tuning strategy to eliminate the discrepancy between the training and inference phases, thereby further improving the reconstruction quality. Extensive experiments demonstrate that the proposed RDEIC achieves state-of-the-art visual quality and outperforms existing diffusion-based extreme image compression methods in both fidelity and efficiency. The source code and pre-trained models are available at https://github.com/huai-chang/RDEIC.","url_abs":"https://arxiv.org/abs/2410.02640v3","url_pdf":"https://arxiv.org/pdf/2410.02640v3.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":"diffusion-based-extreme-image-compression","repo_url":"https://github.com/huai-chang/rdeic","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"denoising","task_name":"Denoising"},{"task_slug":"image-compression","task_name":"Image Compression"}],"methods":[{"method_slug":"diffusion","method_name":"Diffusion"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2410.02640","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.02640"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+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/huai-chang/rdeic","reach":{"status":"ok"}}],"summary":{"ran_draft_wrong":1,"ran_fixture":1,"ran":1,"unverified":2},"by_repo_kind":{"official":{"samples":5,"ran":3,"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":5,"samples":[{"code_sha256_prefix":"7257fdf155f5ef45","entry":"normalize_tensor","repo":"huai-chang/rdeic","repo_kind":"official","path":"model/lpips.py","file_url":"https://github.com/huai-chang/rdeic/blob/HEAD/model/lpips.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"7257fdf155f5ef45"}},{"code_sha256_prefix":"ea9dbc131adf582e","entry":"space_timesteps","repo":"huai-chang/rdeic","repo_kind":"official","path":"model/spaced_sampler_relay.py","file_url":"https://github.com/huai-chang/rdeic/blob/HEAD/model/spaced_sampler_relay.py","link_basis":"harvester_set","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"ea9dbc131adf582e"}},{"code_sha256_prefix":"e268053216b1dd62","entry":"spatial_average","repo":"huai-chang/rdeic","repo_kind":"official","path":"model/lpips.py","file_url":"https://github.com/huai-chang/rdeic/blob/HEAD/model/lpips.py","link_basis":"plan_row","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"e268053216b1dd62"}},{"code_sha256_prefix":"4f8734a02fc01ca2","entry":"find_denominator","repo":"huai-chang/rdeic","repo_kind":"official","path":"model/rdeic.py","file_url":"https://github.com/huai-chang/rdeic/blob/HEAD/model/rdeic.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":"4f8734a02fc01ca2"}},{"code_sha256_prefix":"2cc202bbb038146d","entry":"normalization","repo":"huai-chang/rdeic","repo_kind":"official","path":"model/rdeic.py","file_url":"https://github.com/huai-chang/rdeic/blob/HEAD/model/rdeic.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":"2cc202bbb038146d"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}