Advances in robotic surgery especially in minimally-invasive surgery (MIS) has increased the need for translating computer-vision algorithms in endoscopic imagery to support surgical decisions. While methods for stereo reconstruction have been extensively investigated for man-made environments, such an extensive and detailed study on the pros and cons of stereo reconstruction for endoscopic images. In this paper, we extensively compare several state-of-the-art methods on both simulated as well as real endoscopic images over controlled in-lab and phantom models observed by a daVinci stereo endoscope. The advantages and disadvantages of each compared method over the major steps of a stereo-reconstruction pipeline are discussed and supported by exhaustive experiments and discussions.
Download full-text PDF |
Source |
|---|---|
| http://dx.doi.org/10.1109/EMBC.2014.6944115 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
In the realm of 3D measurement, photometric stereo excels in capturing high-frequency details but suffers from accumulated errors that lead to low-frequency distortions in the reconstructed surface. Conversely, light field (LF) reconstruction provides satisfactory low-frequency geometry but sacrifices spatial resolution, impacting high-frequency detail quality. To tackle these challenges, we propose a photometric stereoscopic light field measurement (PSLFM) scheme that harnesses the strengths of both methods.
View Article and Find Full Text PDFDeep learning has become an attractive tool for addressing the limitations of traditional digital image correlation (DIC). However, extending learning-based DIC methods to three-dimensional (3D-DIC) measurements is challenging due to the limited displacement estimation range, which cannot handle the large displacements caused by stereo-matching disparities. Besides, most of the existing learning-based DIC architectures lack prior information to guide displacement estimation, resulting in insufficient accuracy.
View Article and Find Full Text PDFSegment Any Leaf 3D: A Zero-Shot 3D Leaf Instance Segmentation Method Based on Multi-View Images.
Sensors (Basel)
January 2025
School of Electronic and Communication Engineering, Sun Yat-sen University, Shenzhen 518000, China.
Exploring the relationships between plant phenotypes and genetic information requires advanced phenotypic analysis techniques for precise characterization. However, the diversity and variability of plant morphology challenge existing methods, which often fail to generalize across species and require extensive annotated data, especially for 3D datasets. This paper proposes a zero-shot 3D leaf instance segmentation method using RGB sensors.
View Article and Find Full Text PDFComputed tomography dataset virtual dissection for sternal re-entry in congenital cardiac surgery.
Indian J Thorac Cardiovasc Surg
February 2025
Department of Paediatric and Congenital Heart Surgery, Kokilaben Dhirubhai Ambani Hospital and Medical Research Institute, Rao Saheb, Achutrao Patwardhan Marg, Four Bungalows, Andheri West, Mumbai, Maharashtra 400053 India.
Unlabelled: In congenital heart surgery, redo-sternotomies are very common. In most cases, sternal re-entry is achieved without serious complications. However, sometimes elective institution of peripheral cardiopulmonary bypass is needed for safe sternotomy, albeit with a long cardio-pulmonary bypass time.
View Article and Find Full Text PDFResidual Vision Transformer and Adaptive Fusion Autoencoders for Monocular Depth Estimation.
Sensors (Basel)
December 2024
Institute of Computer and Communication Engineering, Department of Electrical Engineering, National Cheng Kung University, Tainan 701, Taiwan.
Precision depth estimation plays a key role in many applications, including 3D scene reconstruction, virtual reality, autonomous driving and human-computer interaction. Through recent advancements in deep learning technologies, monocular depth estimation, with its simplicity, has surpassed the traditional stereo camera systems, bringing new possibilities in 3D sensing. In this paper, by using a single camera, we propose an end-to-end supervised monocular depth estimation autoencoder, which contains an encoder with a structure with a mixed convolution neural network and vision transformers and an effective adaptive fusion decoder to obtain high-precision depth maps.
View Article and Find Full Text PDFWant AI Summaries of new PubMed Abstracts delivered to your In-box?
Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!