{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,17]],"date-time":"2026-11-17T12:17:40Z","timestamp":1794917860220,"version":"4.9.1"},"publisher-location":"California","reference-count":0,"publisher":"International Joint Conferences on Artificial Intelligence Organization","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,9]]},"abstract":"<jats:p>Recent deep learning-based ISP methods are primarily constrained by mimicking fixed camera pipelines, consequently struggling to achieve expert-level aesthetic quality. To this end, we propose AesISP, the first expert-level aesthetic ISP framework formulated as a reward flow model. Addressing the ill-posed nature of ISP, AesISP establishes a Privileged Prior Distillation paradigm. By leveraging expert-image-guided latent proxies, we decompose the intractable task into a tractable, proxy-driven learning process. Subsequently, we propose MeanFlow++, which reformulates the flow matching objective via target-prediction parameterization and a Progressive Temporal Curriculum. By evolving from learning instantaneous to long-range average velocities, this mechanism rectifies transport trajectories and uses deterministic mapping to impose explicit constraints, anchoring the generation trajectory to the expert manifold. Finally, we introduce a multi-dimensional reward-driven reinforcement learning approach.Leveraging Group Relative Policy Optimization (GRPO) to balance trade-offs across dimensions such as color and lighting, it steers the model to converge precisely on expert-level aesthetic standards. Experiments demonstrate that AesISP outperforms state-of-the-art methods in both quantitative metrics and aesthetic quality.<\/jats:p>","DOI":"10.24963\/ijcai.2026\/174","type":"proceedings-article","created":{"date-parts":[[2026,9,16]],"date-time":"2026-09-16T22:01:13Z","timestamp":1789596073000},"page":"1559-1567","source":"Crossref","is-referenced-by-count":0,"title":["Beyond Pipeline Mimicry: Expert-level Aesthetic ISP via Reward-Guided Flow"],"prefix":"10.24963","author":[{"given":"Tong","family":"Qiao","sequence":"first","affiliation":[{"name":"Xidian University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kepeng","family":"Xu","sequence":"additional","affiliation":[{"name":"Xidian University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Gang","family":"He","sequence":"additional","affiliation":[{"name":"Xidian University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhenyang","family":"Liu","sequence":"additional","affiliation":[{"name":"Xidian University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wenxin","family":"Yu","sequence":"additional","affiliation":[{"name":"Southwest University of Science and Technology"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"10584","event":{"name":"Thirty-Fifth International Joint Conference on Artificial Intelligence {IJCAI-26}","theme":"Artificial Intelligence","location":"Bremen, Germany","acronym":"IJCAI-2026","number":"35","sponsor":["International Joint Conferences on Artificial Intelligence Organization (IJCAI)"],"start":{"date-parts":[[2026,8,15]]},"end":{"date-parts":[[2026,8,21]]}},"container-title":["Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence"],"original-title":[],"deposited":{"date-parts":[[2026,11,17]],"date-time":"2026-11-17T11:28:10Z","timestamp":1794914890000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.ijcai.org\/proceedings\/2026\/174"}},"subtitle":[],"proceedings-subject":"Artificial Intelligence Research Articles","short-title":[],"issued":{"date-parts":[[2026,9]]},"references-count":0,"URL":"https:\/\/doi.org\/10.24963\/ijcai.2026\/174","relation":{},"subject":[],"published":{"date-parts":[[2026,9]]}}}