Evaluating the performance of low-light image enhancement (LLE) is highly subjective, thus making integrating human preferences into image enhancement a necessity. Existing methods fail to consider this and present a series of potentially valid heuristic criteria for training enhancement models. In this paper, we propose a new paradigm, i.e., aesthetics-guided low-light image enhancement (ALL-E), which introduces aesthetic preferences to LLE and motivates training in a reinforcement learning framework with an aesthetic reward. Each pixel, functioning as an agent, refines itself by recursive actions, i.e., its corresponding adjustment curve is estimated sequentially. Extensive experiments show that integrating aesthetic assessment improves both subjective experience and objective evaluation. Our results on various benchmarks demonstrate the superiority of ALL-E over state-of-the-art methods. Source code: https://dongl-group.github.io/project pages/ALLE.html

Silicon oxide (SiO_x) is heralded as the forefront anode material for high‐energy density lithium‐ion batteries, owing to its exceptional specific capacity. Nevertheless, the traditional combination of polyacrylic acid binder and acetylene black conductive carbon continues to struggle with the immense stress induced by the repetitive volume expansion and contraction processes. Here we report a high ionic conductivity, sulfonyl fluoro‐containing binder for SiO_x anode via free radical copolymerization reaction between perfluoro (4‐methyl‐3,6‐dioxaoct‐7‐ene) sulfonyl fluoride and acrylic acid. The electrode fabrication process incorporated amino‐functionalized carbon nanotubes (CNT‐NH₂) as the conductive agent. A three‐dimensional conductive network structure is constructed through physical and chemical double cross‐linking interactions between the ‐COOH and ‐SO₂F functional groups of PAF_0.1 binder, the ‐NH₂ groups of CNT‐NH₂, and the ‐OH groups on the surface of SiO_x, including hydrogen bonds and covalent bonds. In addition, the binder induces the formation of a solid electrolyte interphase (SEI) rich in inorganic components such as Li₂O, Li₂SO₃, Li₂CO₃, and LiF. Benefiting from the synergistic effects of the physically and chemically double cross‐linked three‐dimensional conductive network constructed by the PAF_0.1 binder and CNT‐NH₂, coupled with the rich‐inorganic SEI, the SiO_x anode delivers exceptional rate performance, cycle stability, and lithium‐ion diffusion dynamics.

Removing noise from acquired images is a crucial step in various image processing and computer vision tasks. However, the existing methods primarily focus on removing specific noise and ignore the ability to work across modalities, resulting in limited generalization performance. Inspired by the iterative procedure of image processing used by professionals, we propose a pixel-wise crossmodal image-denoising method based on deep reinforcement learning to effectively handle noise across modalities. We proposed a similarity reward to help teach an optimal action sequence to model the step-wise nature of the human processing process explicitly. In addition, We designed an action set capable of handling multiple types of noise to construct the action space, thereby achieving successful crossmodal denoising. Extensive experiments against state-of-the-art methods on publicly available RGB, infrared, and terahertz datasets demonstrate the superiority of our method in crossmodal image denoising.

Evaluating the performance of low-light image enhancement (LLE) is highly subjective, thus making integrating human preferences into image enhancement a necessity. Existing methods fail to consider this and present a series of potentially valid heuristic criteria for training enhancement models. In this paper, we propose a new paradigm, i.e., aesthetics-guided low-light image enhancement (ALL-E), which introduces aesthetic preferences to LLE and motivates training in a reinforcement learning framework with an aesthetic reward. Each pixel, functioning as an agent, refines itself by recursive actions, i.e., its corresponding adjustment curve is estimated sequentially. Extensive experiments show that integrating aesthetic assessment improves both subjective experience and objective evaluation. Our results on various benchmarks demonstrate the superiority of ALL-E over state-of-the-art methods.