Saved in:
Bibliographic Details
Main Authors: Zhu, Shengjie, Liu, Xiaoming
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2407.19166
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911980121489408
author Zhu, Shengjie
Liu, Xiaoming
author_facet Zhu, Shengjie
Liu, Xiaoming
contents Both self-supervised depth estimation and Structure-from-Motion (SfM) recover scene depth from RGB videos. Despite sharing a similar objective, the two approaches are disconnected. Prior works of self-supervision backpropagate losses defined within immediate neighboring frames. Instead of learning-through-loss, this work proposes an alternative scheme by performing local SfM. First, with calibrated RGB or RGB-D images, we employ a depth and correspondence estimator to infer depthmaps and pair-wise correspondence maps. Then, a novel bundle-RANSAC-adjustment algorithm jointly optimizes camera poses and one depth adjustment for each depthmap. Finally, we fix camera poses and employ a NeRF, however, without a neural network, for dense triangulation and geometric verification. Poses, depth adjustments, and triangulated sparse depths are our outputs. For the first time, we show self-supervision within $5$ frames already benefits SoTA supervised depth and correspondence models. The project page is held in the link (https://shngjz.github.io/SSfM.github.io/).
format Preprint
id arxiv_https___arxiv_org_abs_2407_19166
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Revisit Self-supervised Depth Estimation with Local Structure-from-Motion
Zhu, Shengjie
Liu, Xiaoming
Computer Vision and Pattern Recognition
Both self-supervised depth estimation and Structure-from-Motion (SfM) recover scene depth from RGB videos. Despite sharing a similar objective, the two approaches are disconnected. Prior works of self-supervision backpropagate losses defined within immediate neighboring frames. Instead of learning-through-loss, this work proposes an alternative scheme by performing local SfM. First, with calibrated RGB or RGB-D images, we employ a depth and correspondence estimator to infer depthmaps and pair-wise correspondence maps. Then, a novel bundle-RANSAC-adjustment algorithm jointly optimizes camera poses and one depth adjustment for each depthmap. Finally, we fix camera poses and employ a NeRF, however, without a neural network, for dense triangulation and geometric verification. Poses, depth adjustments, and triangulated sparse depths are our outputs. For the first time, we show self-supervision within $5$ frames already benefits SoTA supervised depth and correspondence models. The project page is held in the link (https://shngjz.github.io/SSfM.github.io/).
title Revisit Self-supervised Depth Estimation with Local Structure-from-Motion
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2407.19166