3 accepted papers
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 il
The rapid growth of large language models raises pressing concerns about intellectual property protection under black-box deployment. Existing backdoor-based fingerprints either rely on rare tokens -- leading to high-perplexity inputs susceptible to filtering -- or use fixed trigger-response mapping…
With the development of perceptual image encryption techniques, visual security evaluations of perceptually encrypted images have gained much attention. Current visual security indices isolate neither global nor local visual security evaluations. They ignore the fact that humans can reorganize parti…