English

Towards Full-parameter and Parameter-efficient Self-learning For Endoscopic Camera Depth Estimation

Computer Vision and Pattern Recognition 2024-10-11 v2 Artificial Intelligence

Abstract

Adaptation methods are developed to adapt depth foundation models to endoscopic depth estimation recently. However, such approaches typically under-perform training since they limit the parameter search to a low-rank subspace and alter the training dynamics. Therefore, we propose a full-parameter and parameter-efficient learning framework for endoscopic depth estimation. At the first stage, the subspace of attention, convolution and multi-layer perception are adapted simultaneously within different sub-spaces. At the second stage, a memory-efficient optimization is proposed for subspace composition and the performance is further improved in the united sub-space. Initial experiments on the SCARED dataset demonstrate that results at the first stage improves the performance from 10.2% to 4.1% for Sq Rel, Abs Rel, RMSE and RMSE log in the comparison with the state-of-the-art models.

Keywords

Cite

@article{arxiv.2410.00979,
  title  = {Towards Full-parameter and Parameter-efficient Self-learning For Endoscopic Camera Depth Estimation},
  author = {Shuting Zhao and Chenkang Du and Kristin Qi and Xinrong Chen and Xinhan Di},
  journal= {arXiv preprint arXiv:2410.00979},
  year   = {2024}
}

Comments

WiCV @ ECCV 2024

R2 v1 2026-06-28T19:04:17.246Z