Related papers: LinK: Linear Kernel for LiDAR-based 3D Perception

We introduce the Linearized Diffusion Map (LDM), a novel linear dimensionality reduction method constructed via a linear approximation of the diffusion-map kernel. LDM integrates the geometric intuition of diffusion-based nonlinear methods…

Convolutional Neural Networks (CNNs) have shown promising results in efficiency and accuracy in image classification. However, their efficacy often relies on large, labeled datasets, posing challenges for applications with limited data…

The recent success of neural networks enables a better interpretation of 3D point clouds, but processing a large-scale 3D scene remains a challenging problem. Most current approaches divide a large-scale scene into small regions and combine…

Accurate 3D imaging is essential for machines to map and interact with the physical world. While numerous 3D imaging technologies exist, each addressing niche applications with varying degrees of success, none have achieved the breadth of…

Dense 3D convolutions provide high accuracy for perception but are too computationally expensive for real-time robotic systems. Existing tri-plane methods rely on 2D image features with interpolation, point-wise queries, and implicit MLPs,…

While 2D object detection has improved significantly over the past, real world applications of computer vision often require an understanding of the 3D layout of a scene. Many recent approaches to 3D detection use LiDAR point clouds for…

Recently, several look-up table (LUT) methods were developed to greatly expedite the inference of CNNs in a classical strategy of trading space for speed. However, these LUT methods suffer from a common drawback of limited receptive field…

The deep convolutional neural networks (CNNs)-based single image dehazing methods have achieved significant success. The previous methods are devoted to improving the network's performance by increasing the network's depth and width. The…

Voxelization is an effective approach to reduce the computational cost of processing Light Detection and Ranging (LiDAR) data, yet it results in a loss of fine-scale structural information. This study explores whether low-level voxel…

Consistent in-focus input imagery is an essential precondition for machine vision systems to perceive the dynamic environment. A defocus blur severely degrades the performance of vision systems. To tackle this problem, we propose a…

Light field is a type of image data that captures the 3D scene information by recording light rays emitted from a scene at various orientations. It offers a more immersive perception than classic 2D images but at the cost of huge data…

Current 3D object detection models follow a single dataset-specific training and testing paradigm, which often faces a serious detection accuracy drop when they are directly deployed in another dataset. In this paper, we study the task of…

This paper presents a new approach to boost a single-modality (LiDAR) 3D object detector by teaching it to simulate features and responses that follow a multi-modality (LiDAR-image) detector. The approach needs LiDAR-image data only when…

Recent progress on 2D object detection has featured Cascade RCNN, which capitalizes on a sequence of cascade detectors to progressively improve proposal quality, towards high-quality object detection. However, there has not been evidence in…

Large Vision Language Models (LVLMs) excel at semantic understanding but struggle with fine grained spatial grounding, as the model must implicitly infer complex geometry without ever producing a spatial interpretation. We present…

Recent advancements in multimodal large language models (LLMs) have demonstrated significant potential across various domains, particularly in concept reasoning. However, their applications in understanding 3D environments remain limited,…

Object detection in challenging situations such as scale variation, occlusion, and truncation depends not only on feature details but also on contextual information. Most previous networks emphasize too much on detailed feature extraction…

Deploying vision foundation models typically relies on efficient adaptation strategies, whereas conventional full fine-tuning suffers from prohibitive costs and low efficiency. While delta-tuning has proven effective in boosting the…

The integration of visual inputs with large language models (LLMs) has led to remarkable advancements in multi-modal capabilities, giving rise to visual large language models (VLLMs). However, effectively harnessing VLLMs for intricate…

This article trained a network for perceiving three-dimensional motion information of binocular vision target, which can provide real-time three-dimensional coordinate, velocity, and acceleration, and has a basic spatiotemporal perception…