Results 21 to 30 of about 429 (147)
Novel view synthesis has experienced significant advancements owing to increasingly capable NeRF- and 3DGS-based methods. However, reflective object reconstruction remains challenging, lacking a proper solution to achieve real-time, high-quality rendering while accommodating inter-reflection.
Yuxuan Yao +4 more
openaire +3 more sources
Fusing Semantic Features with Gaussian Splatting for Enhanced Satellite Image Surface Reconstruction
Reconstructing 3D surfaces from electro-optical satellite imagery is an important capability for generating high-quality digital elevation models at scale.
Albert Reed +3 more
doaj +1 more source
PSHead: 3D Head Reconstruction from a Single Image with Diffusion Prior and Self‐Enhancement
We introduce PSHead, a coarse‐to‐fine framework guided by both object and face priors, to produce a Gaussian‐based 3D avatar for a single frontal‐view reference image. In the coarse stage, we create an initial 3D representation by applying diffusion models trained for general object generation, using Score Distillation Sampling losses over novel views.
Jing Yang +4 more
wiley +1 more source
Modeling Uncertainty for Gaussian Splatting
We present Stochastic Gaussian Splatting (SGS): the first framework for uncertainty estimation using Gaussian Splatting (GS). GS recently advanced the novel-view synthesis field by achieving impressive reconstruction quality at a fraction of the computational cost of Neural Radiance Fields (NeRF).
Aira Luca Savant +2 more
openaire +4 more sources
DiGS: Depth-Initialized Gaussian Splatting for Single-Object Reconstruction
Gaussian Splatting is a state-of-the-art technique for 3D reconstruction. In this paper, we investigate how different initialization strategies influence the optimization process within the Gaussian Splatting framework, showing that more accurate initial
Jacopo Meglioraldi +2 more
doaj +1 more source
HoloGS: Instant Depth-based 3D Gaussian Splatting with Microsoft HoloLens 2 [PDF]
In the fields of photogrammetry, computer vision and computer graphics, the task of neural 3D scene reconstruction has led to the exploration of various techniques.
M. Jäger +5 more
doaj +1 more source
NePO: Neural Point Octrees for Large‐Scale Novel View Synthesis
We introduce Neural Point Octrees (NePOs), a scalable radiance field representation that organises point clouds hierarchically for efficient optimisation and rendering of large scale scenes. NePOs enable level of detail selection, joint refinement of appearance and camera poses, and real‐time rendering of hundreds of millions of points.
Noah Lewis +3 more
wiley +1 more source
SG-Splatting: Accelerating 3D Gaussian Splatting with Spherical Gaussians
3D Gaussian Splatting is emerging as a state-of-the-art technique in novel view synthesis, recognized for its impressive balance between visual quality, speed, and rendering efficiency. However, reliance on third-degree spherical harmonics for color representation introduces significant storage demands and computational overhead, resulting in a large ...
Yiwen Wang, Siyuan Chen, Ran Yi
openaire +2 more sources
Endoscopic imaging has become an indispensable tool in modern medical practice, enabling minimally invasive diagnosis and treatment. A crucial aspect of endoscopic procedures is the accurate reconstruction of the observed scene, which facilitates spatial
Di Ding +4 more
doaj +1 more source
Democratising Multi‐Projector Displays
Spatially augmented reality (SAR) transforms large, surround, collaborative experiences out of VR/AR headsets to the real world by merging content from projectors with the physical environment. This detailed state‐of‐the‐art survey reports on the advancements in multi‐projector aggregation and hardware technologies used to achieve SAR and build ...
Aditi Majumder, Muhammad Twaha Ibrahim
wiley +1 more source

