paper-with-me

Papers

MonoViT: Self-Supervised Monocular Depth Estimation with a Vision Transformer

2022-08-06 · Chaoqiang Zhao, Youmin Zhang, Matteo Poggi, Fabio Tosi, Xianda Guo, Zheng Zhu, Guan Huang, Yang Tang, Stefano Mattoccia

Self-supervised monocular depth estimation is an attractive solution that does not require hard-to-source depth labels for training. Convolutional neural networks (CNNs) have recently achieved great success in this task. However, their limited receptive field constrains existing network architectures to reason only locally, dampening the effectiveness of the self-supervised paradigm. In the light of the recent successes achieved by Vision Transformers (ViTs), we propose MonoViT, a brand-new framework combining the global reasoning enabled by ViT models with the flexibility of self-supervised monocular depth estimation. By combining plain convolutions with Transformer blocks, our model can reason locally and globally, yielding depth prediction at a higher level of detail and accuracy, allowing MonoViT to achieve state-of-the-art performance on the established KITTI dataset. Moreover, MonoViT proves its superior generalization capacities on other datasets such as Make3D and DrivingStereo.

📄 PDF Abstract BibTeX arXiv:2208.03543

Code (1)

zxcqlf/monovit 공식 구현 pytorch

Tasks

Depth EstimationDepth PredictionMonocular Depth EstimationUnsupervised Monocular Depth Estimation

Methods 이 논문이 사용한 방법론

Multi-Head Attention 설명 없음
Attention 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Adam 설명 없음
Absolute Position Encodings Absolute Position Encodings are a type of position embeddings for [Transformer-based models] where positional encodings are…
Position-Wise Feed-Forward Layer 설명 없음

Similar Papers 제목 키워드 기반

SHADeS: Self-supervised Monocular Depth Estimation Through Non-Lambertian Image Decomposition

2025-02-18 · Rema Daher, Francisco Vasconcelos, Danail Stoyanov

Purpose: Visual 3D scene reconstruction can support colonoscopy navigation. It can help in recognising which portions of the colon have been visualised and characterising the size and shape of polyps. This is still a ver…

3D Scene ReconstructionDepth EstimationMonocular Depth Estimation

SelfTune: Metrically Scaled Monocular Depth Estimation through Self-Supervised Learning

2022-03-10 · Jaehoon Choi, Dongki Jung, Yonghan Lee, Deokhwa Kim 외

Monocular depth estimation in the wild inherently predicts depth up to an unknown scale. To resolve scale ambiguity issue, we present a learning algorithm that leverages monocular simultaneous localization and mapping (S…

Depth EstimationMonocular Depth EstimationRobot NavigationSelf-Supervised Learning+1

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

FusionDepth: Complement Self-Supervised Monocular Depth Estimation with Cost Volume

2023-05-10 · Zhuofei Huang, Jianlin Liu, Shang Xu, Ying Chen 외

Multi-view stereo depth estimation based on cost volume usually works better than self-supervised monocular depth estimation except for moving objects and low-textured surfaces. So in this paper, we propose a multi-frame…

Depth EstimationMonocular Depth EstimationStereo Depth Estimation

A high-precision self-supervised monocular visual odometry in foggy weather based on robust cycled generative adversarial networks and multi-task learning aided depth estimation

2022-03-09 · Xiuyuan Li, Jiangang Yu, Fengchao Li, Guowen An

This paper proposes a high-precision self-supervised monocular VO, which is specifically designed for navigation in foggy weather. A cycled generative adversarial network is designed to obtain high-quality self-supervise…

Depth EstimationGenerative Adversarial NetworkMonocular Visual OdometryMulti-Task Learning+2