[PDF] Consistency Regularisation for Unsupervised Domain Adaptation in Monocular Depth Estimation | Semantic Scholar (2024)

[PDF] Semantic Reader

This paper proposes a domain adaptation approach to train a monocular depth estimation model using a fully-annotated source dataset and a non-annotation target dataset, and bridges the domain gap by leveraging semantic predictions and low-level edge features to provide guidance for the target domain.

This work proposes a geometry-aware symmetric domain adaptation framework (GASDA) to explore the labels in the synthetic data and epipolar geometry in the real data jointly and achieves better image style transfer and generates high-quality depth maps.

The proposed AdaDepth - an unsupervised domain adaptation strategy for the pixel-wise regression task of monocular depth estimation performs competitively with other established approaches on depth estimation tasks and achieves state-of-the-art results in a semi-supervised setting.

This paper proposes a novel training objective that enables the convolutional neural network to learn to perform single image depth estimation, despite the absence of ground truth depth data, and produces state of the art results for monocular depth estimation on the KITTI driving dataset.

This paper develops a domain adaptation framework via generating reliable pseudo ground truths of depth from real data to provide direct supervisions and proposes two mechanisms for pseudo-labeling, which improve depth estimation in various settings.

This paper proposes a novel approach to depth map prediction from monocular images that learns in a semi-supervised way and uses sparse ground-truth depth for supervised learning, and also enforces the deep network to produce photoconsistent dense depth maps in a stereo setup using a direct image alignment loss.

This work takes advantage of style transfer and adversarial training to predict pixel perfect depth from a single real-world color image based on training over a large corpus of synthetic environment data.

A fully convolutional architecture, encompassing residual learning, to model the ambiguous mapping between monocular images and depth maps is proposed and a novel way to efficiently learn feature map up-sampling within the network is presented.

This work proposes a post hoc uncertainty estimation approach for an already trained and thus fixed depth estimation model, represented by a deep neural network, that achieves state-of-the-art uncertainty estimation results on the KITTI and NYU Depth V2 benchmarks without the need to retrain the neural network.

This paper presents research in single-image depth prediction using semi-supervised training that outperforms the state-of-the-art, and describes the correct use of ground truth depth derived from LiDAR that can significantly reduce prediction error.

...

...