Related papers: 3D Implicit Transporter for Temporally Consistent …

The objective of this work is to achieve sensorless reconstruction of a 3D volume from a set of 2D freehand ultrasound images with deep implicit representation. In contrast to the conventional way that represents a 3D volume as a discrete…

With the development of 3D laser scanning techniques and depth sensors, 3D dynamic point clouds have attracted increasing attention as a representation of 3D objects in motion, enabling various applications such as 3D immersive…

We introduce VERTEX, an effective solution to recover 3D shape and intrinsic texture of vehicles from uncalibrated monocular input in real-world street environments. To fully utilize the template prior of vehicles, we propose a novel…

Place recognition plays an essential role in the field of autonomous driving and robot navigation. Point cloud based methods mainly focus on extracting global descriptors from local features of point clouds. Despite having achieved…

We introduce KeypointDeformer, a novel unsupervised method for shape control through automatically discovered 3D keypoints. We cast this as the problem of aligning a source 3D object to a target 3D object from the same object category. Our…

LiDAR-based 3D object detection is essential for autonomous driving systems. However, LiDAR point clouds may appear to have sparsity, uneven distribution, and incomplete structures, significantly limiting the detection performance. In road…

Passage retrieval is a fundamental task in many information systems, such as web search and question answering, where both efficiency and effectiveness are critical concerns. In recent years, neural retrievers based on pre-trained language…

3D point clouds deep learning is a promising field of research that allows a neural network to learn features of point clouds directly, making it a robust tool for solving 3D scene understanding tasks. While recent works show that point…

Seamless integration of virtual and physical worlds in augmented reality benefits from the system semantically "understanding" the physical environment. AR research has long focused on the potential of context awareness, demonstrating novel…

We propose a novel neural architecture for representing 3D surfaces, which harnesses two complementary shape representations: (i) an explicit representation via an atlas, i.e., embeddings of 2D domains into 3D; (ii) an implicit-function…

For humans, visual understanding is inherently generative: given a 3D shape, we can postulate how it would look in the world; given a 2D image, we can infer the 3D structure that likely gave rise to it. We can thus translate between the 2D…

In a fully autonomous driving framework, where vehicles operate without human intervention, information sharing plays a fundamental role. In this context, new network solutions have to be designed to handle the large volumes of data…

In this paper, we propose PASS3D to achieve point-wise semantic segmentation for 3D point cloud. Our framework combines the efficiency of traditional geometric methods with robustness of deep learning methods, consisting of two stages: At…

Classification and localization of driving actions over time is important for advanced driver-assistance systems and naturalistic driving studies. Temporal localization is challenging because it requires robustness, reliability, and…

Shape-Text matching is an important task of high-level shape understanding. Current methods mainly represent a 3D shape as multiple 2D rendered views, which obviously can not be understood well due to the structural ambiguity caused by…

Harnessing human movements to command an Unmanned Aerial Vehicle (UAV) holds the potential to revolutionize their deployment, rendering it more intuitive and user-centric. In this research, we introduce a novel methodology adept at…

High-quality surface normal can help improve geometry estimation in problems faced by autonomous vehicles, such as collision avoidance and occlusion inference. While a considerable volume of literature focuses on densely scanned indoor…

We introduce a new trajectory optimization method for robotic grasping based on a point-cloud representation of robots and task spaces. In our method, robots are represented by 3D points on their link surfaces. The task space of a robot is…

Object goal navigation aims to navigate an agent to locations of a given object category in unseen environments. Classical methods explicitly build maps of environments and require extensive engineering while lacking semantic information…

Change detection and irregular object extraction in 3D point clouds is a challenging task that is of high importance not only for autonomous navigation but also for updating existing digital twin models of various industrial environments.…