Seeing Through Smoke: Surgical Desmoking for Improved Visual Perception
This addresses visual perception issues for surgeons during robotic surgery, representing an incremental improvement over existing dehazing and desmoking methods.
The paper tackles the problem of surgical smoke degrading endoscopic imaging during minimally invasive surgery by presenting a transformer-based desmoking model that achieves state-of-the-art performance in image reconstruction, with experiments on a dataset of 5,817 image pairs from the da Vinci robotic system.
Minimally invasive and robot-assisted surgery relies heavily on endoscopic imaging, yet surgical smoke produced by electrocautery and vessel-sealing instruments can severely degrade visual perception and hinder vision-based functionalities. We present a transformer-based surgical desmoking model with a physics-inspired desmoking head that jointly predicts smoke-free image and corresponding smoke map. To address the scarcity of paired smoky-to-smoke-free training data, we develop a synthetic data generation pipeline that blends artificial smoke patterns with real endoscopic images, yielding over 80,000 paired samples for supervised training. We further curate, to our knowledge, the largest paired surgical smoke dataset to date, comprising 5,817 image pairs captured with the da Vinci robotic surgical system, enabling benchmarking on high-resolution endoscopic images. Extensive experiments on both a public benchmark and our dataset demonstrate state-of-the-art performance in image reconstruction compared to existing dehazing and desmoking approaches. We also assess the impact of desmoking on downstream stereo depth estimation and instrument segmentation, highlighting both the potential benefits and current limitations of digital smoke removal methods.