paper-with-me

홈 › Papers

G2-MonoDepth: A General Framework of Generalized Depth Inference from Monocular RGB+X Data

2023-10-24 · Haotian Wang, Meng Yang, Nanning Zheng

Monocular depth inference is a fundamental problem for scene perception of robots. Specific robots may be equipped with a camera plus an optional depth sensor of any type and located in various scenes of different scales, whereas recent advances derived multiple individual sub-tasks. It leads to additional burdens to fine-tune models for specific robots and thereby high-cost customization in large-scale industrialization. This paper investigates a unified task of monocular depth inference, which infers high-quality depth maps from all kinds of input raw data from various robots in unseen scenes. A basic benchmark G2-MonoDepth is developed for this task, which comprises four components: (a) a unified data representation RGB+X to accommodate RGB plus raw depth with diverse scene scale/semantics, depth sparsity ([0%, 100%]) and errors (holes/noises/blurs), (b) a novel unified loss to adapt to diverse depth sparsity/errors of input raw data and diverse scales of output scenes, (c) an improved network to well propagate diverse scene scales from input to output, and (d) a data augmentation pipeline to simulate all types of real artifacts in raw depth maps for training. G2-MonoDepth is applied in three sub-tasks including depth estimation, depth completion with different sparsity, and depth enhancement in unseen scenes, and it always outperforms SOTA baselines on both real-world data and synthetic data.

📄 PDF Abstract BibTeX arXiv:2310.15422

Code (1)

wang-xjtu/g2-monodepth 공식 구현 pytorch

Tasks

Data AugmentationDepth CompletionDepth Estimation

Similar Papers 제목 키워드 기반

Real-time Monocular Depth Estimation on Embedded Systems

2023-08-21 · Cheng Feng, Congxuan Zhang, Zhen Chen, Weiming Hu 외

Depth sensing is of paramount importance for unmanned aerial and autonomous vehicles. Nonetheless, contemporary monocular depth estimation methods employing complex deep neural networks within Convolutional Neural Networ…

Autonomous VehiclesDecoderDepth EstimationMonocular Depth Estimation

RealMonoDepth: Self-Supervised Monocular Depth Estimation for General Scenes

2020-04-14 · Mertalp Ocal, Armin Mustafa

We present a generalised self-supervised learning approach for monocular estimation of the real depth across scenes with diverse depth ranges from 1--100s of meters. Existing supervised methods for monocular depth estima…

Depth EstimationMonocular Depth EstimationSelf-Supervised Learning

MonSter: Marry Monodepth to Stereo Unleashes Power

2025-01-15 · CVPR 2025 1 · Junda Cheng, Longliang Liu, Gangwei Xu, Xianqi Wang 외

Stereo matching recovers depth from image correspondences. Existing methods struggle to handle ill-posed regions with limited matching cues, such as occlusions and textureless areas. To address this, we propose MonSter, …

Depth EstimationMonocular Depth EstimationStereo MatchingZero-shot Generalization

Sparse Auxiliary Networks for Unified Monocular Depth Prediction and Completion

2021-03-30 · CVPR 2021 1 · Vitor Guizilini, Rares Ambrus, Wolfram Burgard, Adrien Gaidon

Estimating scene geometry from data obtained with cost-effective sensors is key for robots and self-driving cars. In this paper, we study the problem of predicting dense depth from a single RGB image (monodepth) with opt…

Depth EstimationDepth PredictionPredictionSelf-Driving Cars+1

Full Surround Monodepth from Multiple Cameras

2021-03-31 · Vitor Guizilini, Igor Vasiljevic, Rares Ambrus, Greg Shakhnarovich 외

Self-supervised monocular depth and ego-motion estimation is a promising approach to replace or supplement expensive depth sensors such as LiDAR for robotics applications like autonomous driving. However, most research i…

Autonomous DrivingMotion Estimation