Results 61 to 70 of about 429 (147)

SFGS-SLAM: Lightweight Image Matching Combined with Gaussian Splatting for a Tracking and Mapping System

Applied Sciences
The integration of SLAM with Gaussian splatting presents a significant challenge: achieving compatibility between real-time performance and high-quality rendering.
Runmin Wang, Zhongliang Deng
doaj   +1 more source

Uncertainty‐Aware Visual Analysis of Force Networks in 2D Granular Materials

Computer Graphics Forum, EarlyView.
Abstract Uncertainty in experimental measurements makes it challenging to determine which features are intrinsic to the phenomenon and which are most stable and reliable. Granular materials, such as sand, form a complex system in which the forces between individual particles influence the material's macroscopic behavior.
M. Evers, A. Naseer, T. G. Murthy, V. Natarajan, T. Bin Masood, D. Weiskopf, I. Hotz   +6 more
wiley   +1 more source

The Truth, the Whole Truth, and Nothing but the Truth: Automatic Visualization Evaluation from Reconstruction Quality

Computer Graphics Forum, EarlyView.
Abstract Recent advances in AI enable the automatic generation of visualizations directly from textual prompts using agentic workflows. However, visualizations produced via one‐shot generative methods often suffer from insufficient quality, typically requiring a human in the loop to refine the outputs.
Roxana Bujack, Li‐Ta Lo, Ethan Stam, Ayan Biswas, David Rogers   +4 more
wiley   +1 more source

HUGS: Human Gaussian Splats

2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
Recent advances in neural rendering have improved both training and rendering times by orders of magnitude. While these methods demonstrate state-of-the-art quality and speed, they are designed for photogrammetry of static scenes and do not generalize well to freely moving humans in the environment.
Kocabas, M. ; https://orcid.org/0000-0001-8593-0415, Chang, J., Gabriel, J., Tuzel, O., Ranjan, A.   +4 more
openaire   +3 more sources

Failing to Reflect Reality: Gaussian Splatting’s Collapse on Non-Lambertian Surfaces

IEEE Open Journal of Signal Processing
We explore the applicability of Gaussian Splatting (GS) to the view synthesis (VS) of non-Lambertian objects. Materials with anisotropic appearance have always been a failure case for VS, until the recent introduction of spherical harmonics promising ...
Eva Dubar, Sarah Dury, Gauthier Lafruit, Daniele Bonatto   +3 more
doaj   +1 more source

As‐Rigid‐As‐Possible Regularization for Implicit Surfaces

Computer Graphics Forum, EarlyView.
Abstract Implicit surface representations have regained popularity because of their use in machine learning. A common component in optimization is regularization, penalizing the deviation of the surface from its original shape. The popular as‐rigid‐as‐possible (Arap) energy strikes a good compromise between realistic deformation behavior and efficient ...
T. Djuren, M. Worchel, U. Finnendahl, M. Alexa   +3 more
wiley   +1 more source

Constrained Dynamic Gaussian Splatting

CoRR
While Dynamic Gaussian Splatting enables high-fidelity 4D reconstruction, its deployment is severely hindered by a fundamental dilemma: unconstrained densification leads to excessive memory consumption incompatible with edge devices, whereas heuristic pruning fails to achieve optimal rendering quality under preset Gaussian budgets.
Zihan Zheng, Zhenglong Wu, Xuanxuan Wang, Houqiang Zhong, Xiaoyun Zhang 0001, Qiang Hu 0003, Guangtao Zhai, Wenjun Zhang 0001   +7 more
openaire   +2 more sources

Meshing Unsigned Distance Fields with Regular Triangulations

Computer Graphics Forum, EarlyView.
Abstract Unsigned distance fields (UDF) are a versatile, implicit representation of geometry. They can represent surfaces that are not bounding a solid or contain points or curves that are not manifold, for example several sheets meeting along a common curve. Contouring the implicit representation, i.e. turning it into an explicit one, requires finding
M. Kohlbrenner, M. Alexa
wiley   +1 more source

Splat-Portrait: Generalizing Talking Heads with Gaussian Splatting

Talking Head Generation aims at synthesizing natural-looking talking videos from speech and a single portrait image. Previous 3D talking head generation methods have relied on domain-specific heuristics such as warping-based facial motion representation priors to animate talking motions, yet still produce inaccurate 3D avatar reconstructions, thus ...
Tong Shi, Melonie de Almeida, Daniela Ivanova, Nicolas Pugeault, Paul Henderson   +4 more
openaire   +2 more sources

Splats in Splats: Robust and Effective 3D Steganography Towards Gaussian Splatting

Proceedings of the AAAI Conference on Artificial Intelligence
3D Gaussian splatting (3DGS) has demonstrated impressive 3D reconstruction performance with explicit scene representations. Given the widespread application of 3DGS in 3D reconstruction and generation tasks, there is an urgent need to protect the copyright of 3DGS assets. However, existing copyright protection techniques for 3DGS overlook the usability
Yijia Guo, Wenkai Huang 0003, Yang Li, Gaolei Li, Hang Zhang 0010, Liwen Hu 0002, Jianhua Li 0001, Tiejun Huang 0001, Lei Ma 0008   +8 more
openaire   +2 more sources