SwinDepth: Unsupervised Depth Estimation using Monocular Sequences via
Swin Transformer and Densely Cascaded Network
- URL: http://arxiv.org/abs/2301.06715v1
- Date: Tue, 17 Jan 2023 06:01:46 GMT
- Title: SwinDepth: Unsupervised Depth Estimation using Monocular Sequences via
Swin Transformer and Densely Cascaded Network
- Authors: Dongseok Shim, H. Jin Kim
- Abstract summary: It is challenging to acquire dense ground truth depth labels for supervised training, and the unsupervised depth estimation using monocular sequences emerges as a promising alternative.
In this paper, we employ a convolution-free Swin Transformer as an image feature extractor so that the network can capture both local geometric features and global semantic features for depth estimation.
Also, we propose a Densely Cascaded Multi-scale Network (DCMNet) that connects every feature map directly with another from different scales via a top-down cascade pathway.
- Score: 29.798579906253696
- License: http://creativecommons.org/licenses/by-sa/4.0/
- Abstract: Monocular depth estimation plays a critical role in various computer vision
and robotics applications such as localization, mapping, and 3D object
detection. Recently, learning-based algorithms achieve huge success in depth
estimation by training models with a large amount of data in a supervised
manner. However, it is challenging to acquire dense ground truth depth labels
for supervised training, and the unsupervised depth estimation using monocular
sequences emerges as a promising alternative. Unfortunately, most studies on
unsupervised depth estimation explore loss functions or occlusion masks, and
there is little change in model architecture in that ConvNet-based
encoder-decoder structure becomes a de-facto standard for depth estimation. In
this paper, we employ a convolution-free Swin Transformer as an image feature
extractor so that the network can capture both local geometric features and
global semantic features for depth estimation. Also, we propose a Densely
Cascaded Multi-scale Network (DCMNet) that connects every feature map directly
with another from different scales via a top-down cascade pathway. This densely
cascaded connectivity reinforces the interconnection between decoding layers
and produces high-quality multi-scale depth outputs. The experiments on two
different datasets, KITTI and Make3D, demonstrate that our proposed method
outperforms existing state-of-the-art unsupervised algorithms.
Related papers
- DepthSplat: Connecting Gaussian Splatting and Depth [90.06180236292866]
In this paper, we present DepthSplat to connect Gaussian splatting and depth estimation.
We first contribute a robust multi-view depth model by leveraging pre-trained monocular depth features.
We also show that Gaussian splatting can serve as an unsupervised pre-training objective.
arXiv Detail & Related papers (2024-10-17T17:59:58Z) - Self-supervised Monocular Depth Estimation with Large Kernel Attention [30.44895226042849]
We propose a self-supervised monocular depth estimation network to get finer details.
Specifically, we propose a decoder based on large kernel attention, which can model long-distance dependencies.
Our method achieves competitive results on the KITTI dataset.
arXiv Detail & Related papers (2024-09-26T14:44:41Z) - Depthformer : Multiscale Vision Transformer For Monocular Depth
Estimation With Local Global Information Fusion [6.491470878214977]
This paper benchmarks various transformer-based models for the depth estimation task on an indoor NYUV2 dataset and an outdoor KITTI dataset.
We propose a novel attention-based architecture, Depthformer for monocular depth estimation.
Our proposed method improves the state-of-the-art by 3.3%, and 3.3% respectively in terms of Root Mean Squared Error (RMSE)
arXiv Detail & Related papers (2022-07-10T20:49:11Z) - HiMODE: A Hybrid Monocular Omnidirectional Depth Estimation Model [3.5290359800552946]
HiMODE is a novel monocular omnidirectional depth estimation model based on a CNN+Transformer architecture.
We show that HiMODE can achieve state-of-the-art performance for 360deg monocular depth estimation.
arXiv Detail & Related papers (2022-04-11T11:11:43Z) - 3DVNet: Multi-View Depth Prediction and Volumetric Refinement [68.68537312256144]
3DVNet is a novel multi-view stereo (MVS) depth-prediction method.
Our key idea is the use of a 3D scene-modeling network that iteratively updates a set of coarse depth predictions.
We show that our method exceeds state-of-the-art accuracy in both depth prediction and 3D reconstruction metrics.
arXiv Detail & Related papers (2021-12-01T00:52:42Z) - VolumeFusion: Deep Depth Fusion for 3D Scene Reconstruction [71.83308989022635]
In this paper, we advocate that replicating the traditional two stages framework with deep neural networks improves both the interpretability and the accuracy of the results.
Our network operates in two steps: 1) the local computation of the local depth maps with a deep MVS technique, and, 2) the depth maps and images' features fusion to build a single TSDF volume.
In order to improve the matching performance between images acquired from very different viewpoints, we introduce a rotation-invariant 3D convolution kernel called PosedConv.
arXiv Detail & Related papers (2021-08-19T11:33:58Z) - PLADE-Net: Towards Pixel-Level Accuracy for Self-Supervised Single-View
Depth Estimation with Neural Positional Encoding and Distilled Matting Loss [49.66736599668501]
We propose a self-supervised single-view pixel-level accurate depth estimation network, called PLADE-Net.
Our method shows unprecedented accuracy levels, exceeding 95% in terms of the $delta1$ metric on the KITTI dataset.
arXiv Detail & Related papers (2021-03-12T15:54:46Z) - Monocular 3D Object Detection with Sequential Feature Association and
Depth Hint Augmentation [12.55603878441083]
FADNet is presented to address the task of monocular 3D object detection.
A dedicated depth hint module is designed to generate row-wise features named as depth hints.
The contributions of this work are validated by conducting experiments and ablation study on the KITTI benchmark.
arXiv Detail & Related papers (2020-11-30T07:19:14Z) - Multi-view Depth Estimation using Epipolar Spatio-Temporal Networks [87.50632573601283]
We present a novel method for multi-view depth estimation from a single video.
Our method achieves temporally coherent depth estimation results by using a novel Epipolar Spatio-Temporal (EST) transformer.
To reduce the computational cost, inspired by recent Mixture-of-Experts models, we design a compact hybrid network.
arXiv Detail & Related papers (2020-11-26T04:04:21Z) - DELTAS: Depth Estimation by Learning Triangulation And densification of
Sparse points [14.254472131009653]
Multi-view stereo (MVS) is the golden mean between the accuracy of active depth sensing and the practicality of monocular depth estimation.
Cost volume based approaches employing 3D convolutional neural networks (CNNs) have considerably improved the accuracy of MVS systems.
We propose an efficient depth estimation approach by first (a) detecting and evaluating descriptors for interest points, then (b) learning to match and triangulate a small set of interest points, and finally (c) densifying this sparse set of 3D points using CNNs.
arXiv Detail & Related papers (2020-03-19T17:56:41Z) - Don't Forget The Past: Recurrent Depth Estimation from Monocular Video [92.84498980104424]
We put three different types of depth estimation into a common framework.
Our method produces a time series of depth maps.
It can be applied to monocular videos only or be combined with different types of sparse depth patterns.
arXiv Detail & Related papers (2020-01-08T16:50:51Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.