☆ 4.7 Article

MonoIndoor plus plus : Towards Better Practice of Self-Supervised Monocular Depth Estimation for Indoor Environments

IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY (2023)

相关参考文献

注意：仅列出部分参考文献，下载原文获取全部文献信息。

Article Engineering, Electrical & Electronic

Depth Estimation Using a Self-Supervised Network Based on Cross-Layer Feature Fusion and the Quadtree Constraint

Fangzheng Tian et al.

Summary: In this paper, a novel self-supervised depth estimation network is proposed, which utilizes a quadtree constraint to optimize the depth estimation network. Photometric loss and depth loss based on quadtree are introduced to address the issue of multiple depth values in repeated structures and uniform texture regions. Experimental results demonstrate that the proposed method outperforms state-of-the-art approaches for depth estimation.

IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY (2022)

添加到收藏夹

Article Engineering, Electrical & Electronic

Fixing Defect of Photometric Loss for Self-Supervised Monocular Depth Estimation

Shu Chen et al.

Summary: View-synthesis-based methods have achieved promising results in unsupervised depth estimation. However, the ambiguity in pose and depth combinations and the violation of the photometric consistency assumption pose challenges. To address these issues, this study proposed using point cloud consistency constraint to eliminate ambiguity, threshold masks to filter dynamic and occluded points, and matching point and epipolar constraints to improve the accuracy and robustness of depth prediction.

IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY (2022)

添加到收藏夹

Article Computer Science, Artificial Intelligence

Towards Robust Monocular Depth Estimation: Mixing Datasets for Zero-Shot Cross-Dataset Transfer

Rene Ranftl et al.

Summary: The success of monocular depth estimation relies on large and diverse training sets. This study proposes tools and methods to mix different datasets and improve the performance of monocular depth estimation.

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE (2022)

添加到收藏夹

Article Computer Science, Artificial Intelligence

Auto-Rectify Network for Unsupervised Indoor Depth Estimation

Jia-Wang Bian et al.

Summary: Single-view depth estimation using CNNs trained from unlabelled videos has achieved excellent results in street-scene driving scenarios, but often fails in other settings. This work identifies the complex ego-motions in handheld settings as a critical obstacle for learning depth, and proposes data pre-processing and an Auto-Rectify Network to address the challenge and achieve significantly improved performance.

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE (2022)

添加到收藏夹

Proceedings Paper Computer Science, Artificial Intelligence

Block-NeRF: Scalable Large Scene Neural View Synthesis

Matthew Tancik et al.

Summary: We propose a variant called Block-NeRF to represent large-scale environments. By decomposing the scene into individually trained NeRFs, rendering time can be decoupled from scene size, enabling rendering in arbitrarily large environments. We also introduce several architectural changes to make NeRF robust to different environmental conditions, and a procedure for aligning appearance between adjacent NeRFs for seamless combination.

2022 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR) (2022)

添加到收藏夹

Proceedings Paper Computer Science, Artificial Intelligence

Swin Transformer V2: Scaling Up Capacity and Resolution

Ze Liu et al.

Summary: This paper presents techniques for scaling Swin Transformer up to 3 billion parameters and the ability to train with high-resolution images. By increasing the capacity and resolution, Swin Transformer achieves new records on four representative vision benchmarks. Several novel technologies are proposed to address training instability and effectively transfer models from low-resolution to high-resolution. Using these techniques and self-supervised pre-training, a strong 3 billion Swin Transformer model is successfully trained, achieving state-of-the-art accuracy on various benchmarks.

2022 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR) (2022)

添加到收藏夹

Article Engineering, Electrical & Electronic

Monocular Depth Estimation Using Laplacian Pyramid-Based Depth Residuals

Minsoo Song et al.

Summary: A new method for monocular depth estimation is proposed in this paper, which effectively utilizes the Laplacian pyramid in the decoder architecture to improve depth estimation accuracy. Additionally, adjusting weight standardization in convolution blocks can improve gradient flow and make optimization smoother.

IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY (2021)

添加到收藏夹

Proceedings Paper Computer Science, Artificial Intelligence

The Temporal Opportunist: Self-Supervised Multi-Frame Monocular Depth

Jamie Watson et al.

Summary: The study introduces a new self-supervised monocular depth estimation method called ManyDepth, which can utilize sequence information at test time, and experiments show that it outperforms existing self-supervised baselines.

2021 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, CVPR 2021 (2021)

添加到收藏夹

Article Engineering, Electrical & Electronic

Monocular Depth Estimation With Augmented Ordinal Depth Relationships

Yuanzhouhan Cao et al.

IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY (2020)

添加到收藏夹

Article Engineering, Electrical & Electronic

Estimating Depth From Monocular Images as Classification Using Deep Fully Convolutional Residual Networks

Yuanzhouhan Cao et al.

IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY (2018)

添加到收藏夹

Article Robotics

ORB-SLAM2: An Open-Source SLAM System for Monocular, Stereo, and RGB-D Cameras

Raul Mur-Artal et al.

IEEE TRANSACTIONS ON ROBOTICS (2017)

添加到收藏夹

Proceedings Paper Computer Science, Artificial Intelligence

A Two-Streamed Network for Estimating Fine-Scaled Depth Maps from Single RGB Images

Jun Li et al.

2017 IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV) (2017)

添加到收藏夹

Proceedings Paper Computer Science, Artificial Intelligence

Unsupervised Monocular Depth Estimation with Left-Right Consistency

Clement Godard et al.

30TH IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2017) (2017)

添加到收藏夹

Proceedings Paper Computer Science, Artificial Intelligence

ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes

Angela Dai et al.

30TH IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2017) (2017)

添加到收藏夹

Article Robotics

The EuRoC micro aerial vehicle datasets

Michael Burri et al.

INTERNATIONAL JOURNAL OF ROBOTICS RESEARCH (2016)

添加到收藏夹

Proceedings Paper Computer Science, Artificial Intelligence

Monocular Depth Estimation Using Neural Regression Forest

Anirban Roy et al.

2016 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR) (2016)

添加到收藏夹

Proceedings Paper Computer Science, Artificial Intelligence

Predicting Depth, Surface Normals and Semantic Labels with a Common Multi-Scale Convolutional Architecture

David Eigen et al.

2015 IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV) (2015)

添加到收藏夹

Article Computer Science, Artificial Intelligence

DepthTransfer: Depth Extraction from Video Using Non-Parametric Sampling

Kevin Karsch et al.

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE (2014)

添加到收藏夹

Article Computer Science, Artificial Intelligence

Make3D: Learning 3D Scene Structure from a Single Still Image

Ashutosh Saxena et al.

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE (2009)

添加到收藏夹

© Peeref 2019-2024. All rights reserved.