Related papers: Unsupervised Learning of Depth, Camera Pose and Op…

In this paper we propose USegScene, a framework for semantically guided unsupervised learning of depth, optical flow and ego-motion estimation for stereo camera images using convolutional neural networks. Our framework leverages semantic…

Learning depth from a single image, as an important issue in scene understanding, has attracted a lot of attention in the past decade. The accuracy of the depth estimation has been improved from conditional Markov random fields,…

We introduce a way to learn to estimate a scene representation from a single image by predicting a low-dimensional subspace of optical flow for each training example, which encompasses the variety of possible camera and object movement.…

Monocular 3D object detection, with the aim of predicting the geometric properties of on-road objects, is a promising research topic for the intelligent perception systems of autonomous driving. Most state-of-the-art methods follow a…

We present a self-supervised learning framework to estimate the individual object motion and monocular depth from video. We model the object motion as a 6 degree-of-freedom rigid-body transformation. The instance segmentation mask is…

Unsupervised learning based depth estimation methods have received more and more attention as they do not need vast quantities of densely labeled data for training which are touch to acquire. In this paper, we propose a novel unsupervised…

In this paper, we introduce a novel training method for making any monocular depth network learn absolute scale and estimate metric road-scene depth just from regular training data, i.e., driving videos. We refer to this training framework…

Accurate monocular metric depth estimation (MMDE) is crucial to solving downstream tasks in 3D perception and modeling. However, the remarkable accuracy of recent MMDE methods is confined to their training domains. These methods fail to…

Monocular depth reconstruction of complex and dynamic scenes is a highly challenging problem. While for rigid scenes learning-based methods have been offering promising results even in unsupervised cases, there exists little to no…

This paper presents an self-supervised deep learning network for monocular visual inertial odometry (named DeepVIO). DeepVIO provides absolute trajectory estimation by directly merging 2D optical flow feature (OFF) and Inertial Measurement…

For ego-motion estimation, the feature representation of the scenes is crucial. Previous methods indicate that both the low-level and semantic feature-based methods can achieve promising results. Therefore, the incorporation of hierarchical…

As a flexible passive 3D sensing means, unsupervised learning of depth from monocular videos is becoming an important research topic. It utilizes the photometric errors between the target view and the synthesized views from its adjacent…

Monocular image-based 3D reconstruction of faces is a long-standing problem in computer vision. Since image data is a 2D projection of a 3D face, the resulting depth ambiguity makes the problem ill-posed. Most existing methods rely on…

Depth estimation from monocular images is a challenging problem in computer vision. In this paper, we tackle this problem using a novel network architecture using multi scale feature fusion. Our network uses two different blocks, first…

Self-supervised monocular depth estimation methods have been increasingly given much attention due to the benefit of not requiring large, labelled datasets. Such self-supervised methods require high-quality salient features and consequently…

Existing monocular depth estimation methods have achieved excellent robustness in diverse scenes, but they can only retrieve affine-invariant depth, up to an unknown scale and shift. However, in some video-based scenarios such as video…

Learning to predict scene depth from RGB inputs is a challenging task both for indoor and outdoor robot navigation. In this work we address unsupervised learning of scene depth and robot ego-motion where supervision is provided by monocular…

Estimating the motion of the camera together with the 3D structure of the scene from a monocular vision system is a complex task that often relies on the so-called scene rigidity assumption. When observing a dynamic environment, this…

Self-supervised deep learning methods have leveraged stereo images for training monocular depth estimation. Although these methods show strong results on outdoor datasets such as KITTI, they do not match performance of supervised methods on…

Self-supervised monocular depth estimation approaches either ignore independently moving objects in the scene or need a separate segmentation step to identify them. We propose MonoDepthSeg to jointly estimate depth and segment moving…