IVCVLGApr 6, 2023

Deep learning-based image exposure enhancement as a pre-processing for an accurate 3D colon surface reconstruction

arXiv:2304.03171v2h-index: 20
Originality Synthesis-oriented
AI Analysis

This work addresses a domain-specific problem for medical imaging and colonoscopy, but it is incremental as it focuses on pre-processing enhancements rather than a novel reconstruction method.

The paper tackled the problem of inaccurate 3D reconstruction in colonoscopy by applying deep learning-based local image exposure correction as a pre-processing step, resulting in improved reconstruction accuracy of the endoscope trajectory.

This contribution shows how an appropriate image pre-processing can improve a deep-learning based 3D reconstruction of colon parts. The assumption is that, rather than global image illumination corrections, local under- and over-exposures should be corrected in colonoscopy. An overview of the pipeline including the image exposure correction and a RNN-SLAM is first given. Then, this paper quantifies the reconstruction accuracy of the endoscope trajectory in the colon with and without appropriate illumination correction

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes