EG 2025 - Short Papers

Permanent URI for this collection

https://diglib.eg.org/handle/10.2312/3607138

Browse

Browsing EG 2025 - Short Papers by Subject "based models"

Now showing 1 - 2 of 2
  • Thumbnail Image
    Item
    NoiseGS: Boosting 3D Gaussian Splatting with Positional Noise for Large-Scale Scene Rendering
    (The Eurographics Association, 2025) Kweon, Minseong; Cheng, Kai; Chen, Xuejin; Park, Jinsun; Ceylan, Duygu; Li, Tzu-Mao
    3D Gaussian Splatting (3DGS) efficiently renders 3D spaces by adaptively densifying anisotropic Gaussians from initial points. However, in complex scenes such as city-scale environments, large Gaussians often overlap with high-frequency regions rich in edges and fine details. In these areas, conflicting per-pixel gradient directions cause gradient cancellation, reducing the overall gradient magnitude and potentially causing Gaussians to remain trapped in suboptimal positions even after densification. To address this, we propose NoiseGS, a novel approach that integrates randomized noise injection into 3DGS, guiding suboptimal Gaussians selected for densification toward more optimal positions. In addition, to mitigate the instability caused by oversized Gaussians, we introduce an ℓp-penalization on the scale of Gaussians. Our method integrates seamlessly with existing heuristicbased optimization and demonstrates strong generalization in reconstructing complex scenes such as MatrixCity and Building.
  • Thumbnail Image
    Item
    TemPCC: Completing Temporal Occlusions in Large Dynamic Point Clouds captured by Multiple RGB-D Cameras
    (The Eurographics Association, 2025) Mühlenbrock, Andre; Weller, Rene; Zachmann, Gabriel; Ceylan, Duygu; Li, Tzu-Mao
    We present TemPCC, an approach to complete temporal occlusions in large dynamic point clouds. Our method manages a point set over time, integrates new observations into this set, and predicts the motion of occluded points based on the flow of surrounding visible ones. Unlike existing methods, our approach efficiently handles arbitrarily large point sets with linear complexity, does not reconstruct a canonical representation, and considers only local features. Our tests, performed on an Nvidia GeForce RTX 4090, demonstrate that our approach can complete a frame with 30,000 points in under 30 ms, while, in general, being able to handle point sets exceeding 1,000,000 points. This scalability enables the mitigation of temporal occlusions across entire scenes captured by multi-RGB-D camera setups. Our initial results demonstrate that self-occlusions are effectively completed and successfully generalized to unknown scenes despite limited training data.