Results 101 to 110 of about 429 (147)
This research introduces an automated 3D virtual reconstruction system tailored for architectural heritage (AH) applications, contributing to the ongoing paradigm shift from traditional CAD-based workflows to artificial intelligence-driven methodologies.
Nelson Montas-Laracuente +6 more
doaj +1 more source
Arbitrary Optics for Gaussian Splatting Using Space Warping
Due to recent advances in 3D reconstruction from RGB images, it is now possible to create photorealistic representations of real-world scenes that only require minutes to be reconstructed and can be rendered in real time.
Jakob Nazarenus +3 more
doaj +1 more source
SGSST: Scaling Gaussian Splatting Style Transfer
Applying style transfer to a full 3D environment is a challenging task that has seen many developments since the advent of neural rendering. 3D Gaussian splatting (3DGS) has recently pushed further many limits of neural rendering in terms of training speed and reconstruction quality. This work introduces SGSST: Scaling Gaussian Splatting Style Transfer,
Bruno Galerne +3 more
openaire +2 more sources
Adaptive Deletion of Gaussian Ellipsoids in 3D Gaussian Splatting
As a leading method for Novel View Synthesis (NVS), 3D Gaussian Splatting (3DGS) faces limitations. Fixed thresholds governing Gaussian scale and opacity lead to over-reconstruction or under-reconstruction, while the linear penalty used for handling ...
Fei Zhang +3 more
doaj +1 more source
SVLGaussian: Single View Language Gaussian Splatting
Open‐vocabulary 3D querying based on 3D Gaussian splatting (3DGS) shows great promise in facilitating accurate 3D query capabilities of AI systems. These methods typically rely on pre‐captured multi‐view images to enable natural language interactions ...
Jiachen Wang +7 more
doaj +1 more source
TGA-GS: Thermal Geometrically Accurate Gaussian Splatting
Novel view synthesis and 3D reconstruction have been extensively studied. Three-dimensional Gaussian Splatting (3DGS) has gained popularity due to its rapid training and real-time rendering capabilities.
Chen Zou +5 more
doaj +1 more source
AdR-Gaussian: Accelerating Gaussian Splatting with Adaptive Radius
SIGGRAPH Asia 2024 Conference Papers (SA Conference Papers '24), December 03-06, 2024, Tokyo ...
Xinzhe Wang, Ran Yi 0002, Lizhuang Ma
openaire +2 more sources
Poison-splat: Computation Cost Attack on 3D Gaussian Splatting
3D Gaussian splatting (3DGS), known for its groundbreaking performance and efficiency, has become a dominant 3D representation and brought progress to many 3D vision tasks. However, in this work, we reveal a significant security vulnerability that has been largely overlooked in 3DGS: the computation cost of training 3DGS could be maliciously tampered ...
Jiahao Lu +4 more
openaire +3 more sources
DiffLiGS: Diffusion-Guided LiDAR-Enhanced 3D Gaussian Splatting
Multi-view 3D reconstruction is essential for smart city, supporting applications such as smart city planning and autonomous navigation. While traditional reconstruction pipelines and recent neural implicit methods, such as NeRF, achieve high visual ...
Shucheng Gong +4 more
doaj +1 more source
Gaussian Billboards: Expressive 2D Gaussian Splatting with Textures
Gaussian Splatting has recently emerged as the go-to representation for reconstructing and rendering 3D scenes. The transition from 3D to 2D Gaussian primitives has further improved multi-view consistency and surface reconstruction accuracy. In this work we highlight the similarity between 2D Gaussian Splatting (2DGS) and billboards from traditional ...
Sebastian Weiss, Derek Bradley
openaire +2 more sources

