Related papers: Iterative Occlusion-Aware Light Field Depth Estima…

The ability to see around corners, i.e., recover details of a hidden scene from its reflections in the surrounding environment, is of considerable interest in a wide range of applications. However, the diffuse nature of light reflected from…

We present an algorithm to estimate fast and accurate depth maps from light fields via a sparse set of depth edges and gradients. Our proposed approach is based around the idea that true depth edges are more sensitive than texture edges to…

Monocular depth estimation has drawn widespread attention from the vision community due to its broad applications. In this paper, we propose a novel physics (geometry)-driven deep learning framework for monocular depth estimation by…

Despite recent advances, estimating optical flow remains a challenging problem in the presence of illumination change, large occlusions or fast movement. In this paper, we propose a novel optical flow estimation framework which can provide…

3D object detection is an essential task in autonomous driving. Recent techniques excel with highly accurate detection rates, provided the 3D input data is obtained from precise but expensive LiDAR technology. Approaches based on cheaper…

HD (High Definition) map based on 3D lidar plays a vital role in autonomous vehicle localization, planning, decision-making, perception, etc. Many 3D lidar mapping technologies related to SLAM (Simultaneous Localization and Mapping) are…

Estimating the 3D position and orientation of objects in the environment with a single RGB camera is a critical and challenging task for low-cost urban autonomous driving and mobile robots. Most of the existing algorithms are based on the…

The problem of identifying the 3D pose of a known object from a given 2D image has important applications in Computer Vision. Our proposed method of registering a 3D model of a known object on a given 2D photo of the object has numerous…

Feature detectors and descriptors are key low-level vision tools that many higher-level tasks build on. Unfortunately these fail in the presence of challenging light transport effects including partial occlusion, low contrast, and…

Supervised learning based methods for monocular depth estimation usually require large amounts of extensively annotated training data. In the case of aerial imagery, this ground truth is particularly difficult to acquire. Therefore, in this…

2D object proposals, quickly detected regions in an image that likely contain an object of interest, are an effective approach for improving the computational efficiency and accuracy of object detection in color images. In this work, we…

Depth estimation is a crucial step for image-guided intervention in robotic surgery and laparoscopic imaging system. Since per-pixel depth ground truth is difficult to acquire for laparoscopic image data, it is rarely possible to apply…

This paper addresses the problem of estimating the 3-DoF camera pose for a ground-level image with respect to a satellite image that encompasses the local surroundings. We propose a novel end-to-end approach that leverages the learning of…

Image composition is a complex task which requires a lot of information about the scene for an accurate and realistic composition, such as perspective, lighting, shadows, occlusions, and object interactions. Previous methods have…

Spherical cameras capture scenes in a holistic manner and have been used for room layout estimation. Recently, with the availability of appropriate datasets, there has also been progress in depth estimation from a single omnidirectional…

Although deep-learning based methods for monocular pedestrian detection have made great progress, they are still vulnerable to heavy occlusions. Using multi-view information fusion is a potential solution but has limited applications, due…

This paper presents a novel indoor layout estimation system based on the fusion of 2D LiDAR and intensity camera data. A ground robot explores an indoor space with a single floor and vertical walls, and collects a sequence of intensity…

Monocular depth estimation (MDE) methods are often either too computationally expensive or not accurate enough due to the trade-off between model complexity and inference performance. In this paper, we propose a lightweight network that can…

Geometric estimation is required for scene understanding and analysis in panoramic 360{\deg} images. Current methods usually predict a single feature, such as depth or surface normal. These methods can lack robustness, especially when…

Depth perception models are typically trained on non-interactive datasets with predefined camera trajectories. However, this often introduces systematic biases into the learning process correlated to specific camera paths chosen during data…