Spatial Correspondence With Generative Adversarial Network: Learning Depth From Monocular Videos
Depth estimation from monocular videos has important applications in many areas such as autonomous driving and robot navigation. It is a very challenging problem without knowing the camera pose since errors in camera-pose estimation can significantly affect the video-based depth estimation accuracy. In this paper, we present a novel SC-GAN network with end-to-end adversarial training for depth estimation from monocular videos without estimating the camera pose and pose change over time. To exploit cross-frame relations, SC-GAN includes a spatial correspondence module which uses Smolyak sparse grids to efficiently match the features across adjacent frames, and an attention mechanism to learn the importance of features in different directions. Furthermore, the generator in SC-GAN learns to estimate depth from the input frames, while the discriminator learns to distinguish between the ground-truth and estimated depth map for the reference frame. Experiments on the KITTI and Cityscapes datasets show that the proposed SC-GAN can achieve much more accurate depth maps than many existing state-of-the-art methods on monocular videos.
Code (0)
등록된 구현이 없습니다.
Tasks
Autonomous DrivingCamera Pose EstimationDepth EstimationGenerative Adversarial NetworkPose EstimationRobot NavigationSimilar Papers 제목 키워드 기반
Unsupervised Adversarial Depth Estimation using Cycled Generative Networks
While recent deep monocular depth estimation approaches based on supervised regression have achieved remarkable performance, costly ground truth annotations are required during training. To cope with this issue, in this …
Depth EstimationMonocular Depth EstimationFocusable Monocular Depth Estimation
Monocular depth foundation models generalize well across scenes, yet they are typically optimized with uniform pixel-wise objectives that do not distinguish user-specified or task-relevant target regions from the surroun…
Monocular Depth EstimationA high-precision self-supervised monocular visual odometry in foggy weather based on robust cycled generative adversarial networks and multi-task learning aided depth estimation
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+2An Adversarial Generative Network Designed for High-Resolution Monocular Depth Estimation from 2D HiRISE Images of Mars
In computer vision, stereoscopy allows the three-dimensional reconstruction of a scene using two 2D images taken from two slightly different points of view, to extract spatial information on the depth of the scene in the…
Depth EstimationGenerative Adversarial NetworkMonocular Depth EstimationStereo Matching+1Y-GAN: A Generative Adversarial Network for Depthmap Estimation from Multi-camera Stereo Images
Depth perception is a key component for autonomous systems that interact in the real world, such as delivery robots, warehouse robots, and self-driving cars. Tasks in autonomous robotics such as 3D object recognition, si…
3D Object RecognitionGenerative Adversarial NetworkObject RecognitionSelf-Driving Cars+1