{"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/qvrf-a-quantization-error-aware-variable-rate","title":"QVRF: A Quantization-error-aware Variable Rate Framework for Learned Image Compression","arxiv_id":"2303.05744","date":"2023-03-10","proceeding":null,"authors":["Kedeng Tong","Yaojun Wu","Yue Li","Kai Zhang","Li Zhang","Xin Jin"],"abstract":"Learned image compression has exhibited promising compression performance, but variable bitrates over a wide range remain a challenge. State-of-the-art variable rate methods compromise the loss of model performance and require numerous additional parameters. In this paper, we present a Quantization-error-aware Variable Rate Framework (QVRF) that utilizes a univariate quantization regulator a to achieve wide-range variable rates within a single model. Specifically, QVRF defines a quantization regulator vector coupled with predefined Lagrange multipliers to control quantization error of all latent representation for discrete variable rates. Additionally, the reparameterization method makes QVRF compatible with a round quantizer. Exhaustive experiments demonstrate that existing fixed-rate VAE-based methods equipped with QVRF can achieve wide-range continuous variable rates within a single model without significant performance degradation. Furthermore, QVRF outperforms contemporary variable-rate methods in rate-distortion performance with minimal additional parameters.","url_abs":"https://arxiv.org/abs/2303.05744v1","url_pdf":"https://arxiv.org/pdf/2303.05744v1.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":"qvrf-a-quantization-error-aware-variable-rate","repo_url":"https://github.com/bytedance/qraf","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null},{"paper_slug":"qvrf-a-quantization-error-aware-variable-rate","repo_url":"https://github.com/VincentChandelier/QRAF","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"qvrf-a-quantization-error-aware-variable-rate","repo_url":"https://github.com/VincentChandelier/ELIC-QVRF","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"qvrf-a-quantization-error-aware-variable-rate","repo_url":"https://github.com/VincentChandelier/GACN-QVRF","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null},{"paper_slug":"qvrf-a-quantization-error-aware-variable-rate","repo_url":"https://github.com/VincentChandelier/SADN-QVRF","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null},{"paper_slug":"qvrf-a-quantization-error-aware-variable-rate","repo_url":"https://github.com/VincentChandelier/STF-QVRF","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"image-compression","task_name":"Image Compression"},{"task_slug":"quantization","task_name":"Quantization"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}