{"ID":5937117,"CreatedAt":"2026-07-07T03:14:33.014478982Z","UpdatedAt":"2026-07-09T12:08:14.305007556Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2607.04985","arxiv_id":"2607.04985","title":"Reduced-complexity Adaptive Loop Filtering via Input-dependent Graph Filters","abstract":"Adaptive Loop Filtering is an important tool for suppressing compression artifacts in modern video codecs. In the enhanced compression model (ECM), a software test model used for experimenting with video coding tools beyond Versatile Video Coding, fixed filters are trained offline and achieve high signal adaptivity via a fine-grained gradient-based classifier, resulting in a large number of fixed filters that introduce redundancy and increased implementation complexity. Reducing this redundancy without compromising artifact suppression, therefore, remains a key challenge. This paper proposes an alternative graph-based fixed-filtering framework for adaptive loop filtering. By using a graph to encode pixel-intensity relationships, our approach captures local structural information more effectively than gradient-based classification alone. Fixed filters are learned as polynomial graph filters, enabling structurally similar local patterns to share common filtering behavior. Experimental results demonstrate that the proposed approach achieves a comparable performance to the ECM baseline while reducing the number of required filters by an order of magnitude.","short_abstract":"Adaptive Loop Filtering is an important tool for suppressing compression artifacts in modern video codecs. In the enhanced compression model (ECM), a software test model used for experimenting with video coding tools beyond Versatile Video Coding, fixed filters are trained offline and achieve high signal adaptivity via...","url_abs":"https://arxiv.org/abs/2607.04985","url_pdf":"https://arxiv.org/pdf/2607.04985v1","authors":"[\"Wen-Yang Lu\",\"Eduardo Pavez\",\"Antonio Ortega\",\"Roman Chernyak\",\"Shan Liu\"]","published":"2026-07-06T12:21:33Z","proceeding":"eess.IV","tasks":"[\"eess.IV\"]","methods":"[]","has_code":false}