AI-based single-shot structured-light depth reconstruction for real-time laparoscopic surgical guidance
2026-08-05 • Robotics
Robotics
AI summaryⓘ
The authors developed a new way to measure depth inside the body during robotic laparoscopic surgery without needing complex equipment or synchronization. They used a simple LED light with a special pattern and a deep learning model that learns from 3D camera data to predict depth from a single image. Their method was accurate, faster, and worked better than some existing models, running smoothly in real-time. They showed it is possible to get reliable 3D information without extra steps like segmenting the image first, but noted that having a large dataset and good calibration is important.
laparoscopic surgerydepth perceptionfringe projection profilometryLED illuminationbinary maskVQ-VAEU-Net3D reconstructionmonocular depth estimationlaser-camera calibration
Authors
Wayne Wonseok Rodgers, Xiangyi Le, Seonghoon Jang, Shuwen Wei, Justin Opfermann, Michael Kam, Axel Krieger, Jin U. Kang
Abstract
Significance. Accurate intraoperative depth perception is important for autonomous and semi-autonomous robotic laparoscopic surgery. Conventional fringe projection profilometry can achieve millimeter-scale accuracy but often requires multi-shot acquisition, digital-micromirror-device projection, and projector-camera synchronization, complicating integration into compact laparoscopic systems. Aim. To develop a synchronization-free, single-shot depth-sensing platform using a passive LED-illuminated binary mask and a VQ-VAE prior with a custom U-Net depth head. Approach. A compact projection module was coupled to one channel of a dual-channel laparoscope, while the second channel imaged the fringe-illuminated target. A Zivid 3D camera acquired reference depth for 722 paired phantom images. Zivid depth maps were reprojected into the SSLE image frame for supervised training and evaluation. The VQ-VAE encoded each input into a discrete latent representation, and a latent-space U-Net predicted depth without a separate mask-prediction branch. Results. Using a fixed train/validation/test split, the proposed model achieved an MAE of 3.70 mm, AbsRel of 0.0326, delta=1.1 accuracy of 0.962, and delta=1.1^2 accuracy of 0.970. It achieved lower MAE than the dual U-Net MaskNet + DepthNet baseline and outperformed off-the-shelf monocular depth models in MAE, AbsRel, and threshold accuracy. The pipeline operated at 26.0 Hz over 301 consecutive frames on an NVIDIA A100 GPU. Conclusions. The LED-illuminated binary-pattern platform with latent-space depth reconstruction enables synchronization-free, video-rate endoscopic depth estimation. Results demonstrate Zivid-referenced phantom reconstruction without an explicit segmentation stage, while emphasizing the importance of dataset size and SSLE-Zivid calibration accuracy.