Related papers: Geometry Uncertainty Projection Network for Monocu…

Unsupervised depth learning takes the appearance difference between a target view and a view synthesized from its adjacent frame as supervisory signal. Since the supervisory signal only comes from images themselves, the resolution of…

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…

Deep learning-based, single-view depth estimation methods have recently shown highly promising results. However, such methods ignore one of the most important features for determining depth in the human vision system, which is motion. We…

Estimating depth from a single image represents an attractive alternative to more traditional approaches leveraging multiple cameras. In this field, deep learning yielded outstanding results at the cost of needing large amounts of data…

Accurate monocular depth estimation is crucial for 3D scene understanding, but existing methods often blur depth at object boundaries, introducing spurious intermediate 3D points. While achieving sharp edges usually requires very…

One of the important parameters for the assessment of glaucoma is optic nerve head (ONH) evaluation, which usually involves depth estimation and subsequent optic disc and cup boundary extraction. Depth is usually obtained explicitly from…

Recent feed-forward networks have achieved remarkable progress in sparse-view 3D reconstruction by predicting dense point maps directly from RGB images. However, they often suffer from geometric inconsistencies and limited fine-grained…

Recognizing and localizing objects in the 3D space is a crucial ability for an AI agent to perceive its surrounding environment. While significant progress has been achieved with expensive LiDAR point clouds, it poses a great challenge for…

We propose SUB-Depth, a universal multi-task training framework for self-supervised monocular depth estimation (SDE). Depth models trained with SUB-Depth outperform the same models trained in a standard single-task SDE framework. By…

This paper proposes 3DGeoDet, a novel geometry-aware 3D object detection approach that effectively handles single- and multi-view RGB images in indoor and outdoor environments, showcasing its general-purpose applicability. The key challenge…

Self-supervised depth learning from monocular images normally relies on the 2D pixel-wise photometric relation between temporally adjacent image frames. However, they neither fully exploit the 3D point-wise geometric correspondences, nor…

In this paper, we introduce a new technique that combines two popular methods to estimate uncertainty in object detection. Quantifying uncertainty is critical in real-world robotic applications. Traditional detection models can be ambiguous…

A single color image can contain many cues informative towards different aspects of local geometric structure. We approach the problem of monocular depth estimation by using a neural network to produce a mid-level representation that…

Mapping and 3D detection are two major issues in vision-based robotics, and self-driving. While previous works only focus on each task separately, we present an innovative and efficient multi-task deep learning framework (SM3D) for…

We propose DFPNet -- an unsupervised, joint learning system for monocular Depth, Optical Flow and egomotion (Camera Pose) estimation from monocular image sequences. Due to the nature of 3D scene geometry these three components are coupled.…

Monocular depth estimation, which plays a crucial role in understanding 3D scene geometry, is an ill-posed problem. Recent methods have gained significant improvement by exploring image-level information and hierarchical features from deep…

Accurate depth estimation is fundamental to 3D perception in autonomous driving, supporting tasks such as detection, tracking, and motion planning. However, monocular camera-based 3D detection suffers from depth ambiguity and reduced…

3D Gaussian splatting has demonstrated impressive performance in real-time novel view synthesis. However, achieving successful reconstruction from RGB images generally requires multiple input views captured under static conditions. To…

Self-supervised learning for depth estimation uses geometry in image sequences for supervision and shows promising results. Like many computer vision tasks, depth network performance is determined by the capability to learn accurate spatial…

Shape completion networks have been used recently in real-world robotic experiments to complete the missing/hidden information in environments where objects are only observed in one or few instances where self-occlusions are bound to occur.…