Results 211 to 220 of about 897,519 (241)
Some of the next articles are maybe not open access.
CGS-SLAM: Compact 3D Gaussian Splatting for Dense Visual SLAM
IEEE/RJS International Conference on Intelligent RObots and SystemsRecent work has shown that 3D Gaussian-based SLAM enables high-quality reconstruction, accurate pose estimation, and real-time rendering of scenes. However, these approaches are built on a tremendous number of redundant 3D Gaussian ellipsoids, leading to
Tianchen Deng +6 more
semanticscholar +1 more source
DashGaussian: Optimizing 3D Gaussian Splatting in 200 Seconds
Computer Vision and Pattern Recognition3D Gaussian Splatting (3DGS) renders pixels by rasterizing Gaussian primitives, where the rendering resolution and the primitive number, concluded as the optimization complexity, dominate the time cost in primitive optimization. In this paper, we propose
Youyu Chen +6 more
semanticscholar +1 more source
Novel Demonstration Generation with Gaussian Splatting Enables Robust One-Shot Manipulation
RoboticsVisuomotor policies learned from teleoperated demonstrations face challenges such as lengthy data collection, high costs, and limited data diversity. Existing approaches address these issues by augmenting image observations in RGB space or employing Real-
Si-Zhe Yang +7 more
semanticscholar +1 more source
YoNoSplat: You Only Need One Model for Feedforward 3D Gaussian Splatting
arXiv.orgFast and flexible 3D scene reconstruction from unstructured image collections remains a significant challenge. We present YoNoSplat, a feedforward model that reconstructs high-quality 3D Gaussian Splatting representations from an arbitrary number of ...
Bo-Tao Ye +4 more
semanticscholar +1 more source
LangSplatV2: High-dimensional 3D Language Gaussian Splatting with 450+ FPS
Neural Information Processing SystemsIn this paper, we introduce LangSplatV2, which achieves high-dimensional feature splatting at 476.2 FPS and 3D open-vocabulary text querying at 384.6 FPS for high-resolution images, providing a 42 $\times$ speedup and a 47 $\times$ boost over LangSplat ...
Wan-Hua Li +6 more
semanticscholar +1 more source
AAAI Conference on Artificial Intelligence
Recently, Gaussian Splatting has sparked a new trend in the field of computer vision. Apart from novel view synthesis, it has also been extended to the area of multi-view reconstruction.
Han Huang +5 more
semanticscholar +1 more source
Recently, Gaussian Splatting has sparked a new trend in the field of computer vision. Apart from novel view synthesis, it has also been extended to the area of multi-view reconstruction.
Han Huang +5 more
semanticscholar +1 more source
International Conference on Learning Representations
Novel view synthesis has long been a practical but challenging task, although the introduction of numerous methods to solve this problem, even combining advanced representations like 3D Gaussian Splatting, they still struggle to recover high-quality ...
Jia-Hao Wu +7 more
semanticscholar +1 more source
Novel view synthesis has long been a practical but challenging task, although the introduction of numerous methods to solve this problem, even combining advanced representations like 3D Gaussian Splatting, they still struggle to recover high-quality ...
Jia-Hao Wu +7 more
semanticscholar +1 more source
VolSplat: Rethinking Feed-Forward 3D Gaussian Splatting with Voxel-Aligned Prediction
arXiv.orgFeed-forward 3D Gaussian Splatting (3DGS) has emerged as a highly effective solution for novel view synthesis. Existing methods predominantly rely on a \emph{pixel-aligned} Gaussian prediction paradigm, where each 2D pixel is mapped to a 3D Gaussian.
Weijie Wang +9 more
semanticscholar +1 more source
Computer Vision and Pattern Recognition
Capturing high-quality photographs under diverse real-world lighting conditions is challenging, as both natural lighting (e.g., low-light) and camera exposure settings (e.g., exposure time) significantly impact image quality.
Ziteng Cui, Xuangeng Chu, Tatsuya Harada
semanticscholar +1 more source
Capturing high-quality photographs under diverse real-world lighting conditions is challenging, as both natural lighting (e.g., low-light) and camera exposure settings (e.g., exposure time) significantly impact image quality.
Ziteng Cui, Xuangeng Chu, Tatsuya Harada
semanticscholar +1 more source
Building Interactable Replicas of Complex Articulated Objects via Gaussian Splatting
International Conference on Learning RepresentationsBuilding articulated objects is a key challenge in computer vision. Existing methods often fail to effectively integrate information across different object states, limiting the accuracy of part-mesh reconstruction and part dynamics modeling ...
Yu Liu +5 more
semanticscholar +1 more source