Related papers: BIT-VO: Visual Odometry at 300 FPS using Binary Fe…
Semi-supervised video object segmentation (VOS) aims to segment a few moving objects in a video sequence, where these objects are specified by annotation of first frame. The optical flow has been considered in many existing semi-supervised…
With the increasing application of robots, stable and efficient Visual Odometry (VO) algorithms are becoming more and more important. Based on the Fourier Mellin Transformation (FMT) algorithm, the extended Fourier Mellin Transformation…
Monocular visual-inertial odometry (VIO) is a low-cost solution to provide high-accuracy, low-drifting pose estimation. However, it has been meeting challenges in vehicular scenarios due to limited dynamics and lack of stable features. In…
This paper introduces SFSORT, the world's fastest multi-object tracking system based on experiments conducted on MOT Challenge datasets. To achieve an accurate and computationally efficient tracker, this paper employs a…
The task of few-shot image classification and segmentation (FS-CS) involves classifying and segmenting target objects in a query image, given only a few examples of the target classes. We introduce the Vision-Instructed Segmentation and…
We propose GSO-SLAM, a real-time monocular dense SLAM system that leverages Gaussian scene representation. Unlike existing methods that couple tracking and mapping with a unified scene, incurring computational costs, or loosely integrate…
We introduce ZeroVO, a novel visual odometry (VO) algorithm that achieves zero-shot generalization across diverse cameras and environments, overcoming limitations in existing methods that depend on predefined or static camera calibration…
Due to the advantages of high computational efficiency and small memory requirements, filter-based visual inertial odometry (VIO) has a good application prospect in miniaturized and payload-constrained embedded systems. However, the…
First-Frame Propagation (FFP) offers a promising paradigm for controllable video editing, but existing methods are hampered by a reliance on cumbersome run-time guidance. We identify the root cause of this limitation as the inadequacy of…
Vision transformers (ViTs) are emerging with significantly improved accuracy in computer vision tasks. However, their complex architecture and enormous computation/storage demand impose urgent needs for new hardware accelerator design…
Lensless imaging enables exceptionally compact fluorescence sensors, advancing applications in \textit{in vivo} imaging and low-cost, point-of-care diagnostics. These sensors require a filter to block the excitation light while passing…
Phase-shifting profilometry (PSP) enables high-accuracy 3D reconstruction but remains highly susceptible to object motion. Although numerous studies have explored compensation for motion-induced errors, residual inaccuracies still persist,…
This paper presents a lightweight LiDAR-inertial-visual odometry system optimized for resource-constrained platforms. It integrates a degeneration-aware adaptive visual frame selector into error-state iterated Kalman filter (ESIKF) with…
The rapid expansion of generative AI drives unprecedented demands for high-performance computing. Training large-scale AI models now requires vast interconnected GPU clusters across multiple data centers. Multi-scale AI training and…
Object detection in point cloud data is one of the key components in computer vision systems, especially for autonomous driving applications. In this work, we present Voxel-FPN, a novel one-stage 3D object detector that utilizes raw data…
Video frame interpolation (VFI) serves as a useful tool for many video processing applications. Recently, it has also been applied in the video compression domain for enhancing both conventional video codecs and learning-based compression…
We present a versatile computational image rendering software of optically-acquired holograms. The reported software can process 4 Megapixel 8-bit raw frames from a sensor array acquired at a sustained rate of 80 Hz. Video-rate image…
We present a dense-indirect SLAM system using external dense optical flows as input. We extend the recent probabilistic visual odometry model VOLDOR [Min et al. CVPR'20], by incorporating the use of geometric priors to 1) robustly bootstrap…
We discuss the performance of a readout system, Fixed Pulse Shape Efficient Readout (FIPSER), to digitize signals from detectors with a fixed pulse shape. In this study we are mainly interested in the readout of fast photon detectors like…
Robust feature matching forms the backbone for most Visual Simultaneous Localization and Mapping (vSLAM), visual odometry, 3D reconstruction, and Structure from Motion (SfM) algorithms. However, recovering feature matches from texture-poor…