Related papers: DeepLiDARFlow: A Deep Learning Architecture For Sc…

Lidars and cameras are critical sensors that provide complementary information for 3D detection in autonomous driving. While prevalent multi-modal methods simply decorate raw lidar point clouds with camera features and feed them directly to…

LiDAR odometry is a fundamental task for various areas such as robotics, autonomous driving. This problem is difficult since it requires the systems to be highly robust running in noisy real-world data. Existing methods are mostly local…

Dense ground displacement measurements are crucial for geological studies but are impractical to collect directly. Traditionally, displacement fields are estimated using patch matching on optical satellite images from different acquisition…

This paper proposes the first non-flow-based deep framework for high dynamic range (HDR) imaging of dynamic scenes with large-scale foreground motions. In state-of-the-art deep HDR imaging, input images are first aligned using optical flows…

Event cameras offer a promising avenue for multi-view stereo depth estimation and Simultaneous Localization And Mapping (SLAM) due to their ability to detect blur-free 3D edges at high-speed and over broad illumination conditions. However,…

Achieving monocular camera localization within pre-built LiDAR maps can bypass the simultaneous mapping process of visual SLAM systems, potentially reducing the computational overhead of autonomous localization. To this end, one of the key…

This paper presents an investigation into the estimation of optical and scene flow using RGBD information in scenarios where the RGB modality is affected by noise or captured in dark environments. Existing methods typically rely solely on…

This paper presents a general framework to build fast and accurate algorithms for video enhancement tasks such as super-resolution, deblurring, and denoising. Essential to our framework is the realization that the accuracy, rather than the…

Accurate 3D object detection is crucial to autonomous driving. Though LiDAR-based detectors have achieved impressive performance, the high cost of LiDAR sensors precludes their widespread adoption in affordable vehicles. Camera-based…

Deep generative models offer a powerful alternative to conventional channel estimation by learning complex channel distributions. By integrating the rich environmental information available in modern sensing-aided networks, this paper…

Depth Completion can produce a dense depth map from a sparse input and provide a more complete 3D description of the environment. Despite great progress made in depth completion, the sparsity of the input and low density of the ground truth…

We present a deep model that can accurately produce dense depth maps given an RGB image with known depth at a very sparse set of pixels. The model works simultaneously for both indoor/outdoor scenes and produces state-of-the-art dense depth…

Deep reinforcement learning has achieved great success in laser-based collision avoidance works because the laser can sense accurate depth information without too much redundant data, which can maintain the robustness of the algorithm when…

Occlusions between consecutive frames have long posed a significant challenge in optical flow estimation. The inherent ambiguity introduced by occlusions directly violates the brightness constancy constraint and considerably hinders…

Fusing the camera and LiDAR information has become a de-facto standard for 3D object detection tasks. Current methods rely on point clouds from the LiDAR sensor as queries to leverage the feature from the image space. However, people…

Visual SLAM (Simultaneous Localization and Mapping) methods typically rely on handcrafted visual features or raw RGB values for establishing correspondences between images. These features, while suitable for sparse mapping, often lead to…

Although LiDAR sensors are crucial for autonomous systems due to providing precise depth information, they struggle with capturing fine object details, especially at a distance, due to sparse and non-uniform data. Recent advances introduced…

This paper introduces a fully deep learning approach to monocular SLAM, which can perform simultaneous localization using a neural network for learning visual odometry (L-VO) and dense 3D mapping. Dense 2D flow and a depth image are…

Realtime 4D reconstruction for dynamic scenes remains a crucial challenge for autonomous driving perception. Most existing methods rely on depth estimation through self-supervision or multi-modality sensor fusion. In this paper, we propose…

We present a stereo-based dense mapping algorithm for large-scale dynamic urban environments. In contrast to other existing methods, we simultaneously reconstruct the static background, the moving objects, and the potentially moving but…