相关论文: Rel3D: A Minimally Contrastive Benchmark for Groun…

3D scene understanding has gained significant attention due to its wide range of applications. However, existing methods for 3D scene understanding are limited to specific downstream tasks, which hinders their practicality in real-world…

Grounding referring expressions in RGBD image has been an emerging field. We present a novel task of 3D visual grounding in single-view RGBD image where the referred objects are often only partially scanned due to occlusion. In contrast to…

Interpreting object-referential language and grounding objects in 3D with spatial relations and attributes is essential for robots operating alongside humans. However, this task is often challenging due to the diversity of scenes, large…

Critical to the registration of point clouds is the establishment of a set of accurate correspondences between points in 3D space. The correspondence problem is generally addressed by the design of discriminative 3D local descriptors on the…

Understanding scene contexts is crucial for machines to perform tasks and adapt prior knowledge in unseen or noisy 3D environments. As data-driven learning is intractable to comprehensively encapsulate diverse ranges of layouts and open…

This study addresses the challenge of performing visual localization in demanding conditions such as night-time scenarios, adverse weather, and seasonal changes. While many prior studies have focused on improving image-matching performance…

Recent advancements in radiance field rendering, exemplified by Neural Radiance Fields (NeRF) and 3D Gaussian Splatting (3DGS), have significantly progressed 3D modeling and reconstruction. The use of multiple 360-degree omnidirectional…

Collaborative 3D object detection exploits information exchange among multiple agents to enhance accuracy of object detection in presence of sensor impairments such as occlusion. However, in practice, pose estimation errors due to imperfect…

Large-scale point cloud generated from 3D sensors is more accurate than its image-based counterpart. However, it is seldom used in visual pose estimation due to the difficulty in obtaining 2D-3D image to point cloud correspondences. In this…

Visual place recognition is a critical task in computer vision, especially for localization and navigation systems. Existing methods often rely on contrastive learning: image descriptors are trained to have small distance for similar images…

We present RELATE, a model that learns to generate physically plausible scenes and videos of multiple interacting objects. Similar to other generative approaches, RELATE is trained end-to-end on raw, unlabeled data. RELATE combines an…

Semantic scene understanding is crucial for robust and safe autonomous navigation, particularly so in off-road environments. Recent deep learning advances for 3D semantic segmentation rely heavily on large sets of training data, however…

Semantic understanding of 3D objects is crucial in many applications such as object manipulation. However, it is hard to give a universal definition of point-level semantics that everyone would agree on. We observe that people have a…

Segmenting humans in 3D indoor scenes has become increasingly important with the rise of human-centered robotics and AR/VR applications. To this end, we propose the task of joint 3D human semantic segmentation, instance segmentation and…

Humans can easily deduce the relative pose of a previously unseen object, without labeling or training, given only a single query-reference image pair. This is arguably achieved by incorporating i) 3D/2.5D shape perception from a single…

Human is able to conduct 3D recognition by a limited number of haptic contacts between the target object and his/her fingers without seeing the object. This capability is defined as `haptic glance' in cognitive neuroscience. Most of the…

Representing and understanding 3D environments in a structured manner is crucial for autonomous agents to navigate and reason about their surroundings. While traditional Simultaneous Localization and Mapping (SLAM) methods generate metric…

We propose to leverage recent advances in reliable 2D pose estimation with Convolutional Neural Networks (CNN) to estimate the 3D pose of people from depth images in multi-person Human-Robot Interaction (HRI) scenarios. Our method is based…

Prior studies on 3D scene understanding have primarily developed specialized models for specific tasks or required task-specific fine-tuning. In this study, we propose Grounded 3D-LLM, which explores the potential of 3D large multi-modal…

Accurate 3D object detection is critical for autonomous driving, necessitating reliable, cost-effective sensors capable of operating in adverse weather conditions. Camera and millimeter-wave radar fusion has emerged as a promising solution;…