Related papers: Deep Depth Estimation from Thermal Image: Dataset,…

Depth cameras are a prominent perception system for robotics, especially when operating in natural unstructured environments. Industrial applications, however, typically involve reflective objects under harsh lighting conditions, a…

Autonomous driving has experienced remarkable progress, bolstered by innovations in computational hardware and sophisticated deep learning methodologies. The foundation of these advancements rests on the availability and quality of…

Datasets have gained an enormous amount of popularity in the computer vision community, from training and evaluation of Deep Learning-based methods to benchmarking Simultaneous Localization and Mapping (SLAM). Without a doubt, synthetic…

Robust SLAM is a crucial enabler for autonomous navigation in natural, semi-structured environments such as parks and gardens. However, these environments present unique challenges for SLAM due to frequent seasonal changes, varying light…

While supervised stereo matching and monocular depth estimation have advanced significantly with learning-based algorithms, self-supervised methods using stereo images as supervision signals have received relatively less focus and require…

We present a new multi-sensor dataset for multi-view 3D surface reconstruction. It includes registered RGB and depth data from sensors of different resolutions and modalities: smartphones, Intel RealSense, Microsoft Kinect, industrial…

Robust perception at night remains challenging for thermal-infrared detection: low contrast and weak high-frequency cues lead to duplicate, overlapping boxes, missed small objects, and class confusion. Prior remedies either translate TIR to…

We introduce Deep Thermal Imaging, a new approach for close-range automatic recognition of materials to enhance the understanding of people and ubiquitous technologies of their proximal environment. Our approach uses a low-cost mobile…

Multi-spectral imagery is invaluable for remote sensing due to different spectral signatures exhibited by materials that often appear identical in greyscale and RGB imagery. Paired with modern deep learning methods, this modality has great…

Clouds are a major obstacle in Earth observation, limiting the usability and reliability of critical remote sensing applications such as fire disaster response, urban heat island monitoring, and snow and ice cover mapping. Therefore, the…

Dense matching is crucial for 3D scene reconstruction since it enables the recovery of scene 3D geometry from image acquisition. Deep Learning (DL)-based methods have shown effectiveness in the special case of epipolar stereo disparity…

Monocular depth estimation is often described as an ill-posed and inherently ambiguous problem. Estimating depth from 2D images is a crucial step in scene reconstruction, 3Dobject recognition, segmentation, and detection. The problem can be…

We consider the problem of reconstructing a dynamic scene observed from a stereo camera. Most existing methods for depth from stereo treat different stereo frames independently, leading to temporally inconsistent depth predictions. Temporal…

Underexposure regions are vital to construct a complete perception of the surroundings for safe autonomous driving. The availability of thermal cameras has provided an essential alternate to explore regions where other optical sensors lack…

Deep models trained on large-scale RGB image datasets have shown tremendous success. It is important to apply such deep models to real-world problems. However, these models suffer from a performance bottleneck under illumination changes.…

Object detection in thermal infrared spectrum provides more reliable data source in low-lighting conditions and different weather conditions, as it is useful both in-cabin and outside for pedestrian, animal, and vehicular detection as well…

Depth estimation is a critical technology in autonomous driving, and multi-camera systems are often used to achieve a 360$^\circ$ perception. These 360$^\circ$ camera sets often have limited or low-quality overlap regions, making multi-view…

Accurate and real-time sensing of targets in three-dimensional (3D) environments is essential for modern machine vision, underpinning emerging technologies such as autonomous systems, robotic manipulation, augmented reality, and intelligent…

Recent self-supervised stereo matching methods have made significant progress, but their performance significantly degrades under adverse weather conditions such as night, rain, and fog. We identify two primary weaknesses contributing to…

Depth sensing is an important problem for 3D vision-based robotics. Yet, a real-world active stereo or ToF depth camera often produces noisy and incomplete depth which bottlenecks robot performances. In this work, we propose D3RoMa, a…