Related papers: 3DV: 3D Dynamic Voxel for Action Recognition in De…
3D object detection has seen quick progress thanks to advances in deep learning on point clouds. A few recent works have even shown state-of-the-art performance with just point clouds input (e.g. VoteNet). However, point cloud data have…
Recent research into human action recognition (HAR) has focused predominantly on skeletal action recognition and video-based methods. With the increasing availability of consumer-grade depth sensors and Lidar instruments, there is a growing…
Detecting actions in videos, particularly within cluttered scenes, poses significant challenges due to the limitations of 2D frame analysis from a camera perspective. Unlike human vision, which benefits from 3D understanding, recognizing…
We propose DeepV2D, an end-to-end deep learning architecture for predicting depth from video. DeepV2D combines the representation ability of neural networks with the geometric principles governing image formation. We compose a collection of…
Tracking dense 3D motion from monocular videos remains challenging, particularly when aiming for pixel-level precision over long sequences. We introduce DELTA, a novel method that efficiently tracks every pixel in 3D space, enabling…
The technology for Visual Odometry (VO) that estimates the position and orientation of the moving object through analyzing the image sequences captured by on-board cameras, has been well investigated with the rising interest in autonomous…
Volumetric video emerges as a new attractive video paradigm in recent years since it provides an immersive and interactive 3D viewing experience with six degree-of-freedom (DoF). Unlike traditional 2D or panoramic videos, volumetric videos…
Event-based cameras can overpass frame-based cameras limitations for important tasks such as high-speed motion detection during self-driving cars navigation in low illumination conditions. The event cameras' high temporal resolution and…
Accurate 3D lane estimation is crucial for ensuring safety in autonomous driving. However, prevailing monocular techniques suffer from depth loss and lighting variations, hampering accurate 3D lane detection. In contrast, LiDAR points offer…
3D Gaussian Splatting has recently shown promising results in dense visual SLAM. However, existing 3DGS-based SLAM methods are all constrained to small-room scenarios and struggle with memory explosion in large-scale scenes and long…
Point cloud video perception has become an essential task for the realm of 3D vision. Current 4D representation learning techniques typically engage in iterative processing coupled with dense query operations. Although effective in…
Dynamic Mode Decomposition (DMD) is a numerical method that seeks to fit timeseries data to a linear dynamical system. In doing so, DMD decomposes dynamic data into spatially coherent modes that evolve in time according to exponential…
3D video coding is one of the most popular research area in multimedia. This paper reviews the recent progress of the coding technologies for multiview video (MVV) and free view-point video (FVV) which is represented by MVV and depth maps.…
The motivation of our work is to present a new visualization-guided computing paradigm to combine direct 3D volume processing and volume rendered clues for effective 3D exploration such as extracting and visualizing microstructures in-vivo.…
Predominant techniques on talking head generation largely depend on 2D information, including facial appearances and motions from input face images. Nevertheless, dense 3D facial geometry, such as pixel-wise depth, plays a critical role in…
We present Hybrid Voxel Network (HVNet), a novel one-stage unified network for point cloud based 3D object detection for autonomous driving. Recent studies show that 2D voxelization with per voxel PointNet style feature extractor leads to…
Learning the spatial-temporal representation of motion information is crucial to human action recognition. Nevertheless, most of the existing features or descriptors cannot capture motion information effectively, especially for long-term…
Existing methods in video action recognition mostly do not distinguish human body from the environment and easily overfit the scenes and objects. In this work, we present a conceptually simple, general and high-performance framework for…
Long-term point tracking is essential to understand non-rigid motion in the physical world better. Deep learning approaches have recently been incorporated into long-term point tracking, but most prior work predominantly functions in 2D.…
Dynamic vision sensors (DVS) are bio-inspired devices that capture visual information in the form of asynchronous events, which encode changes in pixel intensity with high temporal resolution and low latency. These events provide rich…