Related papers: Pointsoup: High-Performance and Extremely Low-Deco…
Recent progress of deep image classification models has provided great potential to improve state-of-the-art performance in related computer vision tasks. However, the transition to semantic segmentation is hampered by strict memory…
3D point clouds are increasingly vital for applications like autonomous driving and robotics, yet the raw data captured by sensors often suffer from noise and sparsity, creating challenges for downstream tasks. Consequently, point cloud…
We introduce a framework for learning latent representations of 4D objects which are descriptive, faithfully capturing object geometry and appearance; compressive, aiding in downstream efficiency; and accessible, requiring minimal input,…
Pre-trained 3D vision models have gained significant attention for their promising performance on point cloud data. However, fully fine-tuning these models for downstream tasks is computationally expensive and storage-intensive. Existing…
Query-based 3D scene instance segmentation from point clouds has attained notable performance. However, existing methods suffer from the query initialization dilemma due to the sparse nature of point clouds and rely on computationally…
Semantic segmentation of raw 3D point clouds is an essential component in 3D scene analysis, but it poses several challenges, primarily due to the non-Euclidean nature of 3D point clouds. Although, several deep learning based approaches…
Event cameras have the ability to capture asynchronous per-pixel brightness changes, called "events", offering advantages over traditional frame-based cameras for computer vision applications. Efficiently coding event data is critical for…
The popularisation of acquisition devices capable of capturing volumetric information such as LiDAR scans and depth cameras has lead to an increased interest in point clouds as an imaging modality. Due to the high amount of data needed for…
Geometry-based point cloud compression (G-PCC), an international standard designed by MPEG, provides a generic framework for compressing diverse types of point clouds while ensuring interoperability across applications and devices. However,…
In autonomous vehicles or robots, point clouds from LiDAR can provide accurate depth information of objects compared with 2D images, but they also suffer a large volume of data, which is inconvenient for data storage or transmission. In…
The Geometry-based Point Cloud Compression (G-PCC) has been developed by the Moving Picture Experts Group to compress point clouds. In its lossy mode, the reconstructed point cloud by G-PCC often suffers from noticeable distortions due to…
To realize low-latency spatial transmission system for immersive telepresence, there are two major problems: capturing dynamic 3D scene densely and processing them in real time. LiDAR sensors capture 3D in real time, but produce sparce…
Object detection in point clouds is an important aspect of many robotics applications such as autonomous driving. In this paper we consider the problem of encoding a point cloud into a format appropriate for a downstream detection pipeline.…
With the great progress of 3D sensing and acquisition technology, the volume of point cloud data has grown dramatically, which urges the development of efficient point cloud compression methods. In this paper, we focus on the task of…
Surface reconstruction from raw point clouds has been studied for decades in the computer graphics community, which is highly demanded by modeling and rendering applications nowadays. Classic solutions, such as Poisson surface…
This letter presents LiteLoc, a novel and efficient localizer built on 3D Gaussian Splatting (3DGS). The previous state-of-the-art (SoTA) sparse-to-dense localizer, STDLoc, has shown remarkable localization capability but suffers from…
The task of point cloud upsampling aims to acquire dense and uniform point sets from sparse and irregular point sets. Although significant progress has been made with deep learning models, state-of-the-art methods require ground-truth dense…
3D point cloud segmentation has a wide range of applications in areas such as autonomous driving, augmented reality, virtual reality and digital twins. The point cloud data collected in real scenes often contain small objects and categories…
Recently, deep learning has significantly advanced the performance of point cloud geometry compression. However, the learning-based lossless attribute compression of point clouds with varying densities is under-explored. In this paper, we…
Deep learning systems extensively use convolution operations to process input data. Though convolution is clearly defined for structured data such as 2D images or 3D volumes, this is not true for other data types such as sparse point…