{"type":"ScholarlyArticle","title":"Beyond Pipeline Mimicry: Expert-level Aesthetic ISP via Reward-Guided Flow","authors":[{"name":"Tong Qiao","slug":"tong-qiao","given":"Tong","family":"Qiao","affiliation":""},{"name":"Kepeng Xu","slug":"kepeng-xu","given":"Kepeng","family":"Xu","affiliation":""},{"name":"Gang He","slug":"gang-he","given":"Gang","family":"He","affiliation":""},{"name":"Zhenyang Liu","slug":"zhenyang-liu","given":"Zhenyang","family":"Liu","affiliation":""},{"name":"Wenxin Yu","slug":"wenxin-yu","given":"Wenxin","family":"Yu","affiliation":""}],"abstract":"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.","doi":"10.24963/ijcai.2026/174","url":"https://ijcai.org/proceedings/2026/174","pdf":"https://ijcai.org/proceedings/2026/0174.pdf","markdown":"https://ijcai.org/proceedings/2026/174.md","bibtex":"https://ijcai.org/proceedings/2026/bibtex/174","volume":{"slug":"2026","title":"Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2026","url":"https://ijcai.org/proceedings/2026/","year":2026,"location":"Bremen, Germany","dates":"15-21 August 2026","editors":"Diego Calvanese","isbn":"978-1-956792-09-6","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2026"},"section":"Computer Vision","track":"Main Track","number":174,"pages":{"first":1559,"last":1567},"keywords":["Computer Vision: Image and video retrieval","Computer Vision: Applications and Systems","Knowledge Representation and Reasoning: Applications"],"videos":[],"references":[],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}