SCARED-C: Corrected Camera Poses for Endoscopic Depth Estimation

TL;DR

SCARED-C enhances the endoscopic depth estimation dataset by applying a structure-from-motion pipeline to correct camera poses, significantly increasing the number of reliable RGB-D pairs for research.

Contribution

The paper introduces SCARED-C, a corrected dataset with improved camera pose accuracy using COLMAP, enabling more extensive and reliable depth estimation experiments.

Findings

Expanded reliable RGB-D pairs from 35 to 17,135.

Validated pose corrections through stereo disparity evaluation.

Improved depth estimation accuracy with the corrected dataset.

Abstract

The SCARED dataset is a widely used benchmark for endoscopic depth estimation, offering ground-truth 3D reconstructions captured with a structured light sensor. However, the depth maps for non-keyframe images rely on robot kinematics that introduce substantial pose errors, limiting the reliably labeled portion of the dataset to 35 keyframes. We present SCARED-C, a corrected version of the SCARED dataset that expands the number of reliable RGB-D pairs from 35 to 17,135. Our pipeline applies COLMAP, a Structure-from-Motion system, to re-estimate camera poses for all frames, followed by a scale recovery step that aligns the resulting reconstructions to metric space using the ground-truth keyframe depth maps. We validate the corrected poses through (1) stereo disparity evaluation and (2) monocular depth estimation experiments. The corrected dataset and code are publicly released to the community.