Max Robotics — Global Service Robot Directory + US Certification

About

Risheng Liu is a researcher specializing in computer vision and image processing, with a particular focus on multi-modality image fusion, underwater visual perception, and deep learning-based scene understanding. His work bridges fundamental vision challenges with real-world robotic and autonomous systems applications. Liu's most influential contribution is his development of multi-interactive feature learning frameworks for simultaneous image fusion and segmentation across multiple modalities. This research, which has garnered over 235 citations since 2023, addresses a critical gap in autonomous driving and robotic operation by achieving strong performance across both fusion and segmentation tasks concurrently — a "best of both worlds" approach that had eluded earlier methods. His introduction of a comprehensive full-time multi-modality benchmark has provided the research community with a valuable evaluation resource. Beyond autonomous systems, Liu has made meaningful strides in underwater visual intelligence, tackling the inherently difficult problem of detecting and enhancing underwater imagery degraded by occlusion, turbidity, and irregular motion. His channel sharpening attention mechanism for underwater species detection (74 citations) and semantic-aware texture-structure enhancement framework (33 citations) demonstrate his sustained commitment to advancing aquatic robotics and marine engineering applications. Collectively, his work reflects a sophisticated integration of attention mechanisms and multi-modal learning to solve demanding real-world perception challenges.