Real-time Monocular 2D and 3D Perception of Endoluminal Scenes for Controlling Flexible Robotic Endoscopic Instruments

Ruofeng Wei; Kai Chen; Yui Lun Ng; Yiyao Ma; Justin Di-Lang Ho; Hon Sing Tong; Xiaomei Wang; Jing Dai

cs.ROFeb 16, 2026

Real-time Monocular 2D and 3D Perception of Endoluminal Scenes for Controlling Flexible Robotic Endoscopic Instruments

Authors: Ruofeng Wei, Kai Chen, Yui Lun Ng, Yiyao Ma, Justin Di-Lang Ho, Hon Sing Tong, Xiaomei Wang, Jing Dai, +2 more

Organizations: Department of Computer Science and Engineering, The Chinese University of Hong Kong, Hong Kong, China. · Department of Mechanical Engineering, The University of Hong Kong, China. · Department of Mechanical and Automation Engineering, The Chinese University of Hong Kong, and also with the Department of Mechanical Engineering, The University of Hong Kong.

Abstract

Endoluminal surgery offers a minimally invasive option for early-stage gastrointestinal and urinary tract cancers but is limited by surgical tools and a steep learning curve. Robotic systems, particularly continuum robots, provide flexible instruments that enable precise tissue resection, potentially improving outcomes. This paper presents a visual perception platform for a continuum robotic system in endoluminal surgery. Our goal is to utilize monocular endoscopic image-based perception algorithms to identify position and orientation of flexible instruments and measure their distances from tissues. We introduce 2D and 3D learning-based perception algorithms and develop a physically-realistic simulator that models flexible instruments dynamics. This simulator generates realistic endoluminal scenes, enabling control of flexible robots and substantial data collection. Using a continuum robot prototype, we conducted module and system-level evaluations. Results show that our algorithms improve control of flexible instruments, reducing manipulation time by over 70% for trajectory-following tasks and enhancing understanding of surgical scenarios, leading to robust endoluminal surgeries.

Figures & tables

Fig. 1: Robotic instrument configurations and endoscopic scenarios in continuum robotic endoluminal surgery. (a) For transurethral bladder tumour resection, the robotic instruments are deployed through a standard urology outer sheath alongside a standard telescope. (b) Two external instrument channels equipped to a standard single-channel GI endoscope (e.g. from Olympus) to deliver the robotic instruments. (c) Monocular endoluminal image captured by GI endoscope.

Fig. 2: Overview of the proposed image-based perception framework for continuum robotic endoluminal surgery. The framework consists of three modules in its hybrid training: 1) 2D continuum robot segmentation module for flexible instruments recognition; 2) 3D robot state estimation module for flexible instrument shape calculation ; and 3) 3D depth estimation module for geometric information provision about the entire endoscopic scene. Monocular endoscopic images serve as the sole input for the perception framework. After training, the framework is deployed on a novel continuum robotic system.

Fig. 3: Calculation of the Per-Pixel Rendering ( PPR ) field from the depth estimation, which is the process of PPR calculation illustrated in Fig. 2 . The PPR field shows a strong correlation with the corresponding input endoscopic image. Arrows from Depth indicate how depth is transformed into attenuation and light direction. Additionally, arrows between Pseudo and Real images represent the correlation computation, with the correlation values normalized to a range of 0 to 1.

Fig. 4: Monocular depth estimation model for continuum robotic endoluminal surgical scene.

Fig. 5: Physically-realistic simulation of continuum robotic system for endoluminal surgery. (a) Setup of the continuum robotic system. (b) Configuration of flexible instruments approximated by curve segments in camera coordinate system. The flexible robot consists of three segments: Shoulder $\widehat{\textbf{OS}}$ , Proximal $\widehat{\textbf{SP}}$ , and Distal $\widehat{\textbf{PD}}$ . $\alpha$ and $\beta$ denote internal bending angles of $\widehat{\textbf{SP}}$ and $\widehat{\textbf{PD}}$ . $\gamma$ and $\delta$ represent $\widehat{\textbf{OS}}$ yaw and roll angles. (c) Comparison of real and synthetic endoscopic images. More comparison results are shown in Video 1.

Fig. 6: Overview of the realistic synthetic continuum robot surgical data generation framework. More synthetic datasets can be found in Video 2.

Fig. 7: 3D texture mapping pipeline for extracting high-quality and continuous textures from endoscopic images and depth information, which is the process in Fig. 6 .

Fig. 8: Examples of synthetic continuum robot surgical data with multiple robot configurations and endoscope scenes.

Method	Left			Right
Method	Dice $\uparrow$	IoU $\uparrow$	Precision $\uparrow$	Dice $\uparrow$	IoU $\uparrow$	Precision $\uparrow$
Syn	38.70	27.93	68.86	15.87	12.09	36.62
Copy-Paste	60.82	48.02	79.34	29.49	20.04	74.74
Ours	94.93	90.38	94.65	95.59	91.60	95.04

TABLE I: Quantitative comparisons for 2D flexible instrument segmentation on ex-vivo data.

\uparrow

indicates that higher values of the corresponding metric represent better performance.

Fig. 9: Performance of flexible instrument segmentation tracking. (a) Examples of instrument segmentation visualization using different approaches during tracking. The semitransparent shadows indicate the predicted segmentations of the instruments. Our results align more accurately with the robotic configuration. (b) Precision comparison of the Ours , Copy-Paste [ 70 ] , and Syn segmentation methods against the ground truth. The numbered circles (1, 2, 3) indicate specific time points that align with the correspondingly numbered images in (a). Values represent the average precision across both left and right instrument segmentations.

Metrics		KP	SKL	Quat	Rot6D	Ours
$\alpha$	Mean $(^{\circ})\downarrow$	22.46	20.61	7.08	4.16	2.60
$\alpha$	Med $(^{\circ})\downarrow$	24.45	22.70	3.09	2.43	2.08
$\beta$	Mean $(^{\circ})\downarrow$	25.82	19.50	7.11	5.54	5.34
$\beta$	Med $(^{\circ})\downarrow$	24.51	19.34	5.24	3.83	3.95
$\gamma$	Mean $(^{\circ})\downarrow$	29.89	17.70	8.31	7.09	6.66
$\gamma$	Med $(^{\circ})\downarrow$	26.34	13.68	6.74	5.44	5.51

TABLE II: Quantitative comparison of our methods with the state-of-the-art methods on testing datasets.

Fig. 10: Qualitative comparison of our continuum robot state estimation model with the state-of-the-art methods: keypoint-based KP [ 28 ] , skeleton-based SKL [ 73 ] , quaternion pose representation Quat [ 33 ] , and rotation 6D pose representation Rot6D [ 34 ] . First, the flexible instruments were manipulated using the estimated state parameters within the proposed simulator. Then, the simulated instruments were projected onto 2D coordinates system to render synthetic images, utilizing the camera extrinsic and intrinsic matrices.

Fig. 11: Performance of continuum robot state tracking. (a) Comparison examples between real and rendered endoscopic images. (b) Variations in tracking error across all estimated robot states over time. The time corresponding to the second frame in (a) with high error is highlighted with a red circle, and its error and uncertainty are presented.

Fig. 12: Qualitative comparison of monocular depth estimation on synthetic and real endoscopic data. The depth estimation results of our model are compared with foundation models Metric3D [ 76 ] and EndoOmni [ 43 ] , finetuned Depth Anything (DA- finetuned ) [ 37 ] , ZoeDepth [ 77 ] and ResNet [ 69 ] . Each row shows flexible robots in the same configuration. Our method captures depth with fine details, where red indicates greater distance from the endoscope and blue indicates proximity.

Metrics	Definition
Abs Rel	$\frac{1}{\|\bm{D}\|}\sum_{d\in\bm{D}}{\|d^{}-d\|/d^{}}$
Sq Rel	$\frac{1}{\|\bm{D}\|}\sum_{d\in\bm{D}}{\|d^{}-d\|^{2}/d^{}}$
RMSE	$\sqrt{\frac{1}{\|\bm{\mathcal{D}}\|}\sum_{d\in\bm{\mathcal{D}}}{\|d^{*}-d\|^{2}}}$
$\text{RMSE}_{log}$	$\sqrt{\frac{1}{\|\bm{D}\|}\sum_{d\in\bm{D}}{\|\log d^{*}-\log d\|^{2}}}$
$\eta$	$\frac{1}{\|\bm{D}\|}\left\{d\in\bm{D}\|\max(\frac{d^{}}{d},\frac{d}{d^{}}<\upsilon)\|\right\}\times 100\%$

TABLE III: Depth Evaluation Metrics

Method	Finetuning	Supervision	$\text{Error}\downarrow$				$\text{Accuracy}\uparrow$
Method	Finetuning	Supervision	Abs Rel	Sq Rel	RMSE	$\text{RMSE}_{log}$	$\eta\!<\!1.25^{1}$	$\eta\!<\!1.25^{2}$	$\eta\!<\!1.25^{3}$
Metric3D [ 76 ]	✗	$-$	0.239	3.671	12.543	0.298	0.494	0.847	0.986
EndoOmni [ 43 ]	✗	$-$	0.273	4.048	11.370	0.354	0.474	0.769	0.92
ResNet [ 69 ]	✓	GT	0.169	1.490	7.703	0.255	0.712	0.917	0.965
ZoeDepth [ 77 ]	✓	GT	0.114	0.857	6.210	0.174	0.867	0.953	0.999
Depth Anything [ 37 ]	✓	GT	0.113	0.806	5.094	0.160	0.858	0.952	0.995

TABLE IV: Quantitative comparisons of monocular depth estimation on synthetic robotic endoluminal test data. GT, ground truth; SSL, self-supervised learning. The best results are in bold. All values in mm .

Fig. 13: Reconstructed 3D point cloud from the monocular depth estimation of real continuum robotic endoluminal surgical data. Variable $i$ denotes the frame index in the video sequence. More results of monocular depth estimation can be found in Video 3.

$\mathcal{L}_{sup}$	PRMod	$\text{Error}\downarrow$				$\text{Accuracy}\uparrow$
$\mathcal{L}_{sup}$	PRMod	Abs Rel	Sq Rel	RMSE	$\text{RMSE}_{log}$	$\eta\!<\!1.25^{1}$
✗	✗	0.096	0.718	4.864	0.150	0.842
✓	✗	0.088	0.610	4.576	0.145	0.870
✗	✓	0.093	0.664	4.728	0.146	0.858
✓	✓	0.072	0.395	4.286	0.102	0.945

TABLE V: Ablation study on

\mathcal{L}_{sup}

and PRMod .

$\bm{\mathcal{F}}_{\text{img}}$	$\bm{\mathcal{F}}_{\text{PPR}}$	$\text{Error}\downarrow$				$\text{Accuracy}\uparrow$
$\bm{\mathcal{F}}_{\text{img}}$	$\bm{\mathcal{F}}_{\text{PPR}}$	Abs Rel	Sq Rel	RMSE	$\text{RMSE}_{log}$	$\eta\!<\!1.25^{1}$
✓	✗	0.074	0.439	4.486	0.107	0.936
✗	✓	0.073	0.399	4.323	0.105	0.943
✓	✓	0.072	0.395	4.286	0.102	0.944

TABLE VI: Ablation study on image features

\bm{\mathcal{F}}_{\text{img}}

and PPR features

\bm{\mathcal{F}}_{\text{PPR}}

Modules	Execution time (ms)
2D segmentation	5.50
3D state estimation	20.72
Subtotal (sequential)	26.22
3D depth estimation (parallel)	47.15
Total system latency	47.15

TABLE VII: Runtime performance of monocular image-based 2D and 3D perception framework.

Fig. 14: Flexible instruments 3D shape monitoring. (a) Examples of endoscopic views alongside the corresponding robotic shapes visualized in the software. The 3D shapes of two instruments are shown from both top and front views. (b) Uncertainty in robot state estimation over time, with fives shapes from (a) marked. Areas with uncertainty values greater than 1 are overlaid with a semi-transparent orange color.

Fig. 15: Failure cases in robot state estimation. Instruments marked with dashed ovals illustrate how partial visibility results in incorrect state estimation and increased uncertainty.

Fig. 16: Analysis of instrument-tissue deviation during flexible instrument touching. (a) Four representative frames along with their corresponding depth maps during the contact events. (b) Variation in distance as the flexible instrument approaches the tissue twice. (c) Multiple views of the 3D structures during the touching events. One demonstration can be found in Video 4.

Explore similar work

Capstan-driven Continuum Surgical Robot: Design, Modeling, and Perception
Aug 13, 2026Gang Zhang, Yufu Qiu, Junyan Yan +3Continuum Robot Control Robot State Estimation
Department of Mechanical and Automation Engineering and T Stone Robotics Institute, The Chinese University of Hong Kong, Hong Kong · School of Mechanical and Electronic Engineering, Wuhan University of Technology, Wuhan 430070, China · state Key Laboratory of Intelligent Manufacturing Equipment and Technology, Huazhong University of Science and Technology (HUST), Wuhan, China +1
MarUco: A Markerless 6D Pose Estimation Framework for Closed-Loop Control of Surgical Continuum Manipulators
Feb 18, 2026Junhyun Park, Chunggil An, Myeongbo Park +3Object Pose Estimation Continuum Robot Control
Department of Robotics and Mechatronics Engineering, DGIST, Daegu 42988, Republic of Korea · AI Research Lab, DEEPNOID, Seoul, Republic of Korea
Contact-Adaptive Robotic Ultrasound Probe Control for Tissue Exploration and Continuous Task-Relevant Visualization Using Robot-Free Image-Motion Demonstration
Sep 27, 2026Seong Jeong, Minsung Kim, Dongho Yee +8Robotic Ultrasound Adaptive Control
Department of Transdisciplinary Medicine, Seoul National University Hospital · Rosota Inc., Seoul, Republic of Korea · Department of Medicine, Seoul National University College of Medicine +6

Aug 13, 2026J/K move · Enter open · S save

Capstan-driven Continuum Surgical Robot: Design, Modeling, and Perception

Gang Zhang, Yufu Qiu, Junyan Yan, Wenhui Zeng+2

Department of Mechanical and Automation Engineering and T Stone Robotics Institute, The Chinese University of Hong Kong, Hong Kong · School of Mechanical and Electronic Engineering, Wuhan University of Technology, Wuhan 430070, China · state Key Laboratory of Intelligent Manufacturing Equipment and Technology, Huazhong University of Science and Technology (HUST), Wuhan, China+1

Continuum Robot Control Robot State Estimation Surgical Robotics

Open paper AskPDF arXiv

Shape and force sensing have long been critical bottlenecks in the development of compact capstan-driven continuum surgical robots, primarily due to the difficulty of obtaining cable tension information within the confined capstan assembly. To overcome these challenges, this paper presents an integrated design-modeling-sensing approach based on the concept of actuation-perception co-design. A compliant element is introduced into the motor mounting bracket of the drive system, enabling micro-deformation under the cable reaction force and thereby allowing real-time cable tension measurement without occupying the compact capstan space. To address the modeling complexity arising from unconventional joint configurations introduced by the spatial cable routing strategy, a parallel computation framework based on a multibody short-thick-beam model is proposed, which captures shear effects in short beam segments and synergistic multi-cable interactions while achieving real-time performance. Building on this framework, stable shape and force sensing is achieved by incorporating a proximal multi-axis force/torque sensor as an additional measurement anchor. Following this design-modeling-sensing framework, capstan-driven continuum surgical robots with single- and dual-segment configurations are developed. Experimental results validate the proposed framework in both single- and dual-segment continuum robots, demonstrating real-time tip pose estimation together with contact force and location perception. By enabling cable tension feedback without compromising the compact capstan architecture, the proposed framework makes integrated perception feasible for capstan-driven continuum surgical robots.

Abstract

Explore similar work

Capstan-driven Continuum Surgical Robot: Design, Modeling, and Perception

MarUco: A Markerless 6D Pose Estimation Framework for Closed-Loop Control of Surgical Continuum Manipulators

Contact-Adaptive Robotic Ultrasound Probe Control for Tissue Exploration and Continuous Task-Relevant Visualization Using Robot-Free Image-Motion Demonstration