paper-with-me

Papers

GeoRefine: Self-Supervised Online Depth Refinement for Accurate Dense Mapping

2022-05-03 · Pan Ji, Qingan Yan, Yuxin Ma, Yi Xu

We present a robust and accurate depth refinement system, named GeoRefine, for geometrically-consistent dense mapping from monocular sequences. GeoRefine consists of three modules: a hybrid SLAM module using learning-based priors, an online depth refinement module leveraging self-supervision, and a global mapping module via TSDF fusion. The proposed system is online by design and achieves great robustness and accuracy via: (i) a robustified hybrid SLAM that incorporates learning-based optical flow and/or depth; (ii) self-supervised losses that leverage SLAM outputs and enforce long-term geometric consistency; (iii) careful system design that avoids degenerate cases in online depth refinement. We extensively evaluate GeoRefine on multiple public datasets and reach as low as $5\%$ absolute relative depth errors.

📄 PDF Abstract BibTeX arXiv:2205.01656

Code (0)

등록된 구현이 없습니다.

Tasks

Optical Flow Estimation

Similar Papers 제목 키워드 기반

SA4Depth: Consistent Pose-Depth Scale Alignment for Self-Supervised Monocular Depth Estimation

2026-05-27 · Changxuan Li, Nadine Berner, Nassir Navab, Federico Tombari 외 arxiv

Self-supervised depth estimation from monocular sequences relies on the joint learning of a depth and a pose network. Despite abundant research done to improve the depth network, efforts on the pose remain limited. In th…

Monocular Depth Estimation

Self-Supervised Monocular Depth Estimation with Self-Reference Distillation and Disparity Offset Refinement

2023-02-20 · Zhong Liu, Ran Li, Shuwei Shao, Xingming Wu 외

Monocular depth estimation plays a fundamental role in computer vision. Due to the costly acquisition of depth ground truth, self-supervised methods that leverage adjacent frames to establish a supervisory signal have em…

Depth EstimationMonocular Depth Estimation

Self-supervised Learning with Geometric Constraints in Monocular Video: Connecting Flow, Depth, and Camera

2019-07-12 · ICCV 2019 10 · Yuhua Chen, Cordelia Schmid, Cristian Sminchisescu

We present GLNet, a self-supervised framework for learning depth, optical flow, camera pose and intrinsic parameters from monocular video - addressing the difficulty of acquiring realistic ground-truth for such tasks. We…

Monocular Depth EstimationOptical Flow EstimationSelf-Supervised LearningTransfer Learning+1

DualRefine: Self-Supervised Depth and Pose Estimation Through Iterative Epipolar Sampling and Refinement Toward Equilibrium

2023-04-07 · CVPR 2023 1 · Antyanta Bangunharcana, Ahmed Magd, Kyung-Soo Kim

Self-supervised multi-frame depth estimation achieves high accuracy by computing matching costs of pixel correspondences between adjacent frames, injecting geometric information into the network. These pixel-corresponden…

Depth EstimationDepth PredictionPose Estimation

UM-Depth : Uncertainty Masked Self-Supervised Monocular Depth Estimation with Visual Odometry

2025-09-17 · Tae-Wook Um, Ki-Hyeon Kim, Hyun-Duck Choi, Hyo-Sung Ahn arxiv

Monocular depth estimation has been increasingly adopted in robotics and autonomous driving for its ability to infer scene geometry from a single camera. In self-supervised monocular depth estimation frameworks, the netw…

Monocular Depth EstimationAutonomous DrivingPose EstimationVisual Odometry