Related papers: Dual Attribute-Spatial Relation Alignment for 3D V…

Deep learning approaches have made tremendous progress in the field of semantic segmentation over the past few years. However, most current approaches operate in the 2D image space. Direct semantic segmentation of unstructured 3D point…

Recent advancements in weakly-supervised video anomaly detection have achieved remarkable performance by applying the multiple instance learning paradigm based on multimodal foundation models such as CLIP to highlight anomalous instances…

Two factors have proven to be very important to the performance of semantic segmentation models: global context and multi-level semantics. However, generating features that capture both factors always leads to high computational complexity,…

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…

Segment matching is an important intermediate task in computer vision that establishes correspondences between semantically or geometrically coherent regions across images. Unlike keypoint matching, which focuses on localized features,…

Estimating the 3D structure of the drivable surface and surrounding environment is a crucial task for assisted and autonomous driving. It is commonly solved either by using 3D sensors such as LiDAR or directly predicting the depth of points…

To perform tasks specified by natural language instructions, autonomous agents need to extract semantically meaningful representations of language and map it to visual elements and actions in the environment. This problem is called…

The prosperity of deep learning contributes to the rapid progress in scene text detection. Among all the methods with convolutional networks, segmentation-based ones have drawn extensive attention due to their superiority in detecting text…

Representation learning from 3D point clouds is challenging due to their inherent nature of permutation invariance and irregular distribution in space. Existing deep learning methods follow a hierarchical feature extraction paradigm in…

Localizing 3D objects using natural language is essential for robotic scene understanding. The descriptions often involve multiple spatial relationships to distinguish similar objects, making 3D-language alignment difficult. Current methods…

3D Visual Grounding (3DVG) seeks to locate target objects in 3D scenes using natural language descriptions, enabling downstream applications such as augmented reality and robotics. Existing approaches typically rely on labeled 3D data and…

Effective scene representation is critical for the visual grounding ability of representations, yet existing methods for 3D Visual Grounding are often constrained. They either only focus on geometric and visual cues, or, like traditional 3D…

The segmentation of satellite images is crucial in remote sensing applications. Existing methods face challenges in recognizing small-scale objects in satellite images for semantic segmentation primarily due to ignoring the low-level…

LiDAR sensors are widely used for 3D object detection in various mobile robotics applications. LiDAR sensors continuously generate point cloud data in real-time. Conventional 3D object detectors detect objects using a set of points acquired…

Due to the wide applications of X-ray computed tomography (CT) in medical imaging activities, radiation exposure has become a major concern for public health. Sparse-view CT is a promising approach to reduce the radiation dose by…

There are two main issues in RGB-D salient object detection: (1) how to effectively integrate the complementarity from the cross-modal RGB-D data; (2) how to prevent the contamination effect from the unreliable depth map. In fact, these two…

Aiming to link natural language descriptions to specific regions in a 3D scene represented as 3D point clouds, 3D visual grounding is a very fundamental task for human-robot interaction. The recognition errors can significantly impact the…

Object detection from 3D point clouds remains a challenging task, though recent studies pushed the envelope with the deep learning techniques. Owing to the severe spatial occlusion and inherent variance of point density with the distance to…

Service robots should be able to interact naturally with non-expert human users, not only to help them in various tasks but also to receive guidance in order to resolve ambiguities that might be present in the instruction. We consider the…

3D object grounding aims to locate the most relevant target object in a raw point cloud scene based on a free-form language description. Understanding complex and diverse descriptions, and lifting them directly to a point cloud is a new and…