Related papers: FFAM: Feature Factorization Activation Map for Exp…
Multiresolution analysis and matrix factorization are foundational tools in computer vision. In this work, we study the interface between these two distinct topics and obtain techniques to uncover hierarchical block structure in symmetric…
In this paper, we introduce FMapping, an efficient neural field mapping framework that facilitates the continuous estimation of a colorized point cloud map in real-time dense RGB SLAM. To achieve this challenging goal without depth, a…
Matrix factorization (MF) is a classical collaborative filtering algorithm for recommender systems. It decomposes the user-item interaction matrix into a product of low-dimensional user representation matrix and item representation matrix.…
Recent advances in vision foundation models have revolutionized geometry reconstruction and semantic understanding. Yet, most of the existing approaches treat these capabilities in isolation, leading to redundant pipelines and compounded…
Feature point (FP) detection is a fundamental step of many computer vision tasks. However, FP detectors are usually designed for low dynamic range (LDR) images. In scenes with extreme light conditions, LDR images present saturated pixels,…
Finding localized correspondences across different images of the same object is crucial to understand its geometry. In recent years, this problem has seen remarkable progress with the advent of deep learning-based local image features and…
Camera and LiDAR sensor modalities provide complementary appearance and geometric information useful for detecting 3D objects for autonomous vehicle applications. However, current end-to-end fusion methods are challenging to train and…
Fusing LiDAR and camera information is essential for achieving accurate and reliable 3D object detection in autonomous driving systems. This is challenging due to the difficulty of combining multi-granularity geometric and semantic features…
Multi-camera-based 3D object detection has made notable progress in the past several years. However, we observe that there are cases (e.g. faraway regions) in which popular 2D object detectors are more reliable than state-of-the-art 3D…
State-of-the-art LiDAR-camera 3D object detectors usually focus on feature fusion. However, they neglect the factor of depth while designing the fusion strategy. In this work, we are the first to observe that different modalities play…
Multi-sensor fusion (MSF) is widely used in autonomous vehicles (AVs) for perception, particularly for 3D object detection with camera and LiDAR sensors. The purpose of fusion is to capitalize on the advantages of each modality while…
Nowadays, deep neural networks for object detection in images are very prevalent. However, due to the complexity of these networks, users find it hard to understand why these objects are detected by models. We proposed Gaussian Class…
In this paper we introduce a novel way to predict semantic information from sparse, single-shot LiDAR measurements in the context of autonomous driving. In particular, we fuse learned features from complementary representations. The…
Foundation models are vital tools in various Computer Vision applications. They take as input a single RGB image and output a deep feature representation that is useful for various applications. However, in case we have multiple views of…
The LiDAR 3D object detector that strikes a balance between accuracy and speed is crucial for achieving real-time perception in autonomous driving. However, many existing LiDAR detection models depend on complex feature transformations,…
Lidars and cameras play essential roles in autonomous driving, offering complementary information for 3D detection. The state-of-the-art fusion methods integrate them at the feature level, but they mostly rely on the learned soft…
Feature matching is crucial in visual localization, where 2D-3D correspondence plays a major role in determining the accuracy of camera pose. A sufficient number of well-distributed 2D-3D correspondences is essential for accurate pose…
Cooperatively utilizing both ego-vehicle and infrastructure sensor data can significantly enhance autonomous driving perception abilities. However, the uncertain temporal asynchrony and limited communication conditions can lead to fusion…
Increasing demands for understanding the internal behavior of convolutional neural networks (CNNs) have led to remarkable improvements in explanation methods. Particularly, several class activation mapping (CAM) based methods, which…
Recent camera-based 3D object detection is limited by the precision of transforming from image to 3D feature spaces, as well as the accuracy of object localization within the 3D space. This paper aims to address such a fundamental problem…