AdaDepth: Unsupervised Content Congruent Adaptation for Depth Estimation

@article{Kundu2018AdaDepthUC,
  title={AdaDepth: Unsupervised Content Congruent Adaptation for Depth Estimation},
  author={Jogendra Nath Kundu and Phani Krishna Uppala and Anuj Pahuja and R. Venkatesh Babu},
  journal={2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year={2018},
  pages={2656-2665}
}
Supervised deep learning methods have shown promising results for the task of monocular depth estimation; but acquiring ground truth is costly, and prone to noise as well as inaccuracies. [] Key Method The proposed approach is devoid of above limitations through a) adversarial learning and b) explicit imposition of content consistency on the adapted target representation. Our unsupervised approach performs competitively with other established approaches on depth estimation tasks and achieves state-of-the-art…

Figures and Tables from this paper

Learn to Adapt for Monocular Depth Estimation
TLDR
This work proposes an adversarial depth estimation task and proposes a constraint to impose upon cross-task depth consistency to compel the depth estimation to be identical in different adversarial tasks, which improves the performance of the method and smoothens the training process.
Unsupervised Adversarial Depth Estimation Using Cycled Generative Networks
TLDR
A novel unsupervised deep learning approach for predicting depth maps and showing that the depth estimation task can be effectively tackled within an adversarial learning framework is presented.
Domain Adaptive Monocular Depth Estimation With Semantic Information
TLDR
This paper proposes an adversarial training model that leverages semantic information to narrow the domain gap and achieves the state-of-the-art performance comparable to complex latest models and show favorable results on boundaries and objects at far distances.
Learning a Domain-Agnostic Visual Representation for Autonomous Driving via Contrastive Loss
TLDR
A Domain-Agnostic Contrastive Learning (DACL) which is a two-stage unsupervised domain adaptation framework with cyclic adversarial training and contrastive loss leads the neural network to learn domain-agnostic representation to overcome performance degradation when there exists a difference between training and test data distribution.
Efficient unsupervised monocular depth estimation using attention guided generative adversarial network
TLDR
This paper proposes a computationally efficient GAN for unsupervised monocular depth estimation using factorized convolutions and an attention mechanism, and proposes a context-aware attention architecture to generate detail-oriented depth images.
Structured Coupled Generative Adversarial Networks for Unsupervised Monocular Depth Estimation
TLDR
A new end-to-end unsupervised deep learning framework for monocular depth estimation consisting of two Generative Adversarial Networks (GAN), deeply coupled with a structured Conditional Random Field (CRF) model to fuse the generative and discriminative outputs from the dual GAN nets.
Progressive Fusion for Unsupervised Binocular Depth Estimation Using Cycled Networks
TLDR
This paper introduces a new network architecture, named Progressive Fusion Network (PFN), that is specifically designed for binocular stereo depth estimation, based on a multi-scale refinement strategy that combines the information provided by both stereo views.
Geometry-Aware Symmetric Domain Adaptation for Monocular Depth Estimation
TLDR
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.
CoMoDA: Continuous Monocular Depth Adaptation Using Past Experiences
TLDR
This paper proposes a novel self-supervised Continuous Monocular Depth Adaptation method (CoMoDA), which adapts the pretrained model on a test video on the fly and achieves state-of-the-art depth estimation performance and surpass all existing methods using standard architectures.
Learning Depth from Monocular Videos Using Synthetic Data: A Temporally-Consistent Domain Adaptation Approach
TLDR
A temporally-consistent domain adaptation (TCDA) approach that simultaneously explores labels in the synthetic domain and temporal constraints in the videos to improve style transfer and depth prediction and makes use of the ground-truth optical flow and pose information in the Synthetic data to learn moving mask and pose prediction networks.
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 55 REFERENCES
FCNs in the Wild: Pixel-level Adversarial and Constraint-based Adaptation
TLDR
This paper introduces the first domain adaptive semantic segmentation method, proposing an unsupervised adversarial approach to pixel prediction problems, and outperforms baselines across different settings on multiple large-scale datasets.
Unsupervised Monocular Depth Estimation with Left-Right Consistency
TLDR
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.
Unsupervised CNN for Single View Depth Estimation: Geometry to the Rescue
TLDR
This work proposes a unsupervised framework to learn a deep convolutional neural network for single view depth prediction, without requiring a pre-training stage or annotated ground-truth depths, and shows that this network trained on less than half of the KITTI dataset gives comparable performance to that of the state-of-the-art supervised methods for singleView depth estimation.
Deeper Depth Prediction with Fully Convolutional Residual Networks
TLDR
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.
Semi-Supervised Deep Learning for Monocular Depth Map Prediction
TLDR
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.
Adversarial Discriminative Domain Adaptation
TLDR
It is shown that ADDA is more effective yet considerably simpler than competing domain-adversarial methods, and the promise of the approach is demonstrated by exceeding state-of-the-art unsupervised adaptation results on standard domain adaptation tasks as well as a difficult cross-modality object classification task.
Render for CNN: Viewpoint Estimation in Images Using CNNs Trained with Rendered 3D Model Views
TLDR
A scalable and overfit-resistant image synthesis pipeline, together with a novel CNN specifically tailored for the viewpoint estimation task, is proposed that can significantly outperform state-of-the-art methods on PASCAL 3D+ benchmark.
Deep convolutional neural fields for depth estimation from a single image
TLDR
A deep structured learning scheme which learns the unary and pairwise potentials of continuous CRF in a unified deep CNN framework and can be used for depth estimations of general scenes with no geometric priors nor any extra information injected.
Deep Exemplar 2D-3D Detection by Adapting from Real to Rendered Views
This paper presents an end-to-end convolutional neural network (CNN) for 2D-3D exemplar detection. We demonstrate that the ability to adapt the features of natural images to better align with those
Improved Techniques for Training GANs
TLDR
This work focuses on two applications of GANs: semi-supervised learning, and the generation of images that humans find visually realistic, and presents ImageNet samples with unprecedented resolution and shows that the methods enable the model to learn recognizable features of ImageNet classes.
...
1
2
3
4
5
...