Related papers: Volkit: A Performance-Portable Computer Vision Lib…
In this paper, we study Multiscale Vision Transformers (MViTv2) as a unified architecture for image and video classification, as well as object detection. We present an improved version of MViT that incorporates decomposed relative…
The availability of city-scale Lidar maps enables the potential of city-scale place recognition using mobile cameras. However, the city-scale Lidar maps generally need to be compressed for storage efficiency, which increases the difficulty…
The virtual reality (VR) provides us a three-dimensional, immersive, and fully interactive visualization environment. To make the best use of the VR's potential in scientific visualization, a VR visualization software named VFIVE has been…
We address the problem of 3D object detection, that is, estimating 3D object bounding boxes from point clouds. 3D object detection methods exploit either voxel-based or point-based features to represent 3D objects in a scene. Voxel-based…
This paper introduces DroneVis, a novel library designed to automate computer vision algorithms on Parrot drones. DroneVis offers a versatile set of features and provides a diverse range of computer vision tasks along with a variety of…
Recent efforts to enhance immersive and interactive user experiences have driven the development of volumetric video, a form of 3D content that enables 6 DoF. Unlike traditional 2D content, volumetric content can be represented in various…
We present an optimization study of the Vision-Language Frontier Maps (VLFM) applied to the Object Goal Navigation task in robotics. Our work evaluates the efficiency and performance of various vision-language models, object detectors,…
Recent Vision Transformer (ViT)-based methods for Image Super-Resolution have demonstrated impressive performance. However, they suffer from significant complexity, resulting in high inference times and memory usage. Additionally, ViT…
We present Voxel Transformer (VoTr), a novel and effective voxel-based Transformer backbone for 3D object detection from point clouds. Conventional 3D convolutional backbones in voxel-based 3D detectors cannot efficiently capture large…
The CAVE-type virtual reality (VR) system was introduced for scientific visualization of large scale data in the plasma simulation community about a decade ago. Since then, we have been developing a VR visualization software, VFIVE, for…
This is the preprint version of our paper on ICONIP2015. The proposed platform supports the integrated VRGIS functions including 3D spatial analysis functions, 3D visualization for spatial process and serves for 3D globe and digital city.…
Recent open-vocabulary 3D scene understanding approaches mainly focus on training 3D networks through contrastive learning with point-text pairs or by distilling 2D features into 3D models via point-pixel alignment. While these methods show…
Understanding 3D scenes semantically and spatially is crucial for the safe navigation of robots and autonomous vehicles, aiding obstacle avoidance and accurate trajectory planning. Camera-based 3D semantic occupancy prediction, which infers…
VTX is an open-source molecular visualization software designed to overcome the scaling limitations of existing real-time molecular visualization software when handling massive molecular datasets. VTX employs a meshless molecular graphics…
Vision Transformers (ViTs) excel in semantic segmentation but demand significant computation, posing challenges for deployment on resource-constrained devices. Existing token pruning methods often overlook fundamental visual data…
We introduce the Bandicoot C++ library for linear algebra and scientific computing on GPUs, overviewing its user interface and performance characteristics, as well as the technical details of its internal design. Bandicoot is the…
We present an open-source toolkit for neural machine translation (NMT). The new toolkit is mainly based on vaulted Transformer (Vaswani et al., 2017) along with many other improvements detailed below, in order to create a self-contained,…
Current LiDAR point cloud-based 3D single object tracking (SOT) methods typically rely on point-based representation network. Despite demonstrated success, such networks suffer from some fundamental problems: 1) It contains pooling…
Vision-language pre-training (VLP) has recently proven highly effective for various uni- and multi-modal downstream applications. However, most existing end-to-end VLP methods use high-resolution image-text box data to perform well on…
Vision Transformers (ViTs) represent a groundbreaking shift in machine learning approaches to computer vision. Unlike traditional approaches, ViTs employ the self-attention mechanism, which has been widely used in natural language…