This work systematically investigates Gaussian initialization strategies and proposes a simple yet effective scheme tailored for VolVis scenes, improving reconstruction accuracy and accelerating convergence, and evaluates ECoNGS qualitatively and quantitatively across various univariate and multivariate VolVis scenes.
Abstract
Recent advances in differentiable Gaussian splatting have highlighted the potential of primitive-based approaches as alternative scene representations for interactive, high-quality, volume visualization (VolVis) of large datasets. However, the explicit nature of current primitive-based methods, combined with isolated optimization for each VolVis scene, results in redundant, non-compact representations. We present ECoNGS, an efficient compressive neural Gaussian splatting framework for VolVis scene representation. ECoNGS employs lightweight neural networks to dynamically predict implicit, editable Gaussian splats from explicit anchor points, effectively combining model compactness and parameter efficiency of implicit representations with high-performance rendering of explicit primitives. We explore a joint learning strategy that clusters geometrically similar scenes and shares parameters across them, significantly reducing overall training time and model size while maintaining reconstruction fidelity. To achieve a more compact scene representation, we further compress the explicit anchor attributes using a neural entropy model that estimates their probability distributions, enabling compact storage via entropy coding. We systematically investigate Gaussian initialization strategies and propose a simple yet effective scheme tailored for VolVis scenes, improving reconstruction accuracy and accelerating convergence. We evaluate ECoNGS qualitatively and quantitatively across various univariate and multivariate VolVis scenes, highlighting its superior performance over prior methods in training time, reconstruction quality, and model size. In particular, compared with the prior method iVR-GS, ECoNGS improves reconstruction quality by up to 2.2 dB in PSNR while reducing the model size by up to 6.1x and the training time by up to 5.9x. The code is available at https://github.com/TouKaienn/ECoNGS.
Explicit primitive-based radiance fields such as 3D Gaussian Splatting typically model view-dependent appearance using low-order spherical harmonics (SH). Although efficient to evaluate, SH coefficients dominate per-primitive storage and memory traffic, while their band-limited basis restricts angular detail. We present a thorough, end-to-end comparison of SH and recent spherical appearance models and introduce an implicit alternative that decodes compact per-primitive latent codes using a tiny shared MLP. We integrate all models into the same optimized pipeline, fusing their forward and backward passes into a differentiable CUDA rasterizer and provide a portable WebGL viewer for laptop and mobile GPUs. Our evaluation across reconstruction quality, memory use, and optimization and rendering performance shows that recent spherical models offer the strongest overall quality-efficiency trade-off. Our neural representation is the most compact model evaluated and, compared to third-degree SH, reduces the per-primitive appearance footprint from 192 to 28 bytes, accelerates optimization by 1.3$\times$, while improving reconstruction quality. We further analyze how appearance parametrization shapes optimization, identifying differences in recovered geometry and the tendency of expressive models to absorb non-static scene content. Together, our framework and analysis provide practical guidance for replacing SH beyond what image metrics alone can capture.
Florian Hahlbohm, Jorge Condor, Linus Franke et al.· 0 citations
ParticleGS is a visualization-aware framework based on 3D Gaussian Splatting (3DGS) that learns a compact representation directly optimized for rendered image quality, combining a multi-stage, multi-orbit training pipeline and a lightweight network that adapts a single trained model to user-specified visualization parameters at inference time.
Bo Jiang, You-Yuan Liu, Taolue Yang et al.· arXiv.org· 1 citation
Recent advances in neural scene representations enable photorealistic novel-view synthesis, yet most methods remain tightly coupled to a single rendering paradigm, limiting their versatility and integration with conventional graphics workflows. We introduce Floating Radiance Networks (FlaRe), a neural scene representation combining explicit ray-traceable geometry with continuous neural radiance functions. A scene is represented by floating planar generalized Gaussian primitives, each carrying a compact latent descriptor of a local radiance field. A lightweight decoder shared across the scene maps this descriptor, local surface coordinates, and viewing direction to color and opacity. This formulation preserves the expressiveness of neural fields while providing an explicitly addressable structure that can be efficiently queried and manipulated. Hardware-accelerated primitive intersections enable interactive rendering and recursive ray-tracing, including reflections, refractions, transparency, and shadows. The same representation further supports primitive-level deformation, mesh extraction, and appearance stylization directly in its learned descriptor space. Experiments across standard reconstruction benchmarks demonstrate competitive rendering quality while using a compact set of primitives. Together, these results establish FlaRe as a versatile representation that brings high-fidelity neural rendering, ray-tracing, geometric manipulation, and appearance editing into a unified scene model. Source code is available online. Source code can be found at: https://github.com/KByrski/FlaRe
K. Byrski, Rafal Tobiasz, Grzegorz Wilczynski et al.· 0 citations
3D Gaussian Splatting has become a de facto scene representation for novel view synthesis, yet robustly learning 3D Gaussian primitives from visual input remains challenging. Standard optimization relies on gradient-based updates, but a common issue is the gradient vanishing phenomenon: a pixel far from a Gaussian primitive often has diminishing gradient magnitudes to influence primitive attributes, resulting in suboptimal scene reconstruction. In this paper, we propose a method to address gradient vanishing with a piecewise truncated gradient formulation that improves the optimization stability and robustness to initializations. We show that our method consistently improves 3D Gaussian Splatting with random and COLMAP initializations while being generalizable across static and dynamic Gaussian Splatting. As a by-product, we also examine the limitations of current benchmarks for dynamic scenes, and introduce a novel dataset for benchmarking dynamic Gaussian Splatting using synthetic 3D scenes. We demonstrate the effectiveness of our method in both static and dynamic settings for the public benchmarks and our proposed dataset.
Théo Morales, Nhat-Quynh Le-Pham, Robin Atkins et al.· 0 citations
The proposed framework provides a simple and effective path toward fast and inherently compact 3DGS training, and leverages a synergistic design: an L2 reconstruction loss to provide error-proportional gradients that stabilize optimization, and a novel Polarized Opacity Prior to actively manage the Gaussian population.
Zi-Ming Wang, Kai-Wen Duan, Ko-Wei Huang et al.· 0 citations
The advancement of digital media technologies has greatly expanded the need for realistic and artistically expressive 3D content. As an emerging technology, 3D scene stylization, which transfers artistic characteristics from reference images to reconstructed 3D scenes, has become a prominent research direction in computer vision and computer graphics. Although Neural Radiance Fields (NeRF)-based approaches have achieved promising results in stylized novel view synthesis, they still suffer from issues such as slow optimization, high computational cost, and susceptibility to geometric artifacts. Recently, 3D Gaussian Splatting has demonstrated superior efficiency and real-time rendering capabilities. However, its discrete structure and fixed geometry restrict the accurate representation of continuous textures and fine-grained style features across multiple views. To overcome these limitations, we propose Graph-Guided Adaptive Gaussian Splatting for Scene Stylization (GAGS)—an efficient 3D scene stylization framework for Gaussian Splatting representations. First, we leverage a pre-trained 3DGS scene representation as the foundation and introduce a style-aware alignment module. This module learns cross-view style patterns to capture fine-grained, high-frequency texture information, thereby ensuring multi-view consistency. Next, we propose to construct a spatial adjacency graph over Gaussian ellipsoids to identify inter-ellipsoid style discrepancies and fuse style features from neighboring regions. In addition, we propose a Style-Intensity-Aware Gaussian Refinement module. Leveraging the previously constructed adjacency graph, this mechanism adaptively adjusts the sizes of Gaussian ellipsoids according to node affinities, thereby achieving effective stylization while preventing geometric distortion. Compared with state-of-the-art methods, our proposed approach can generate high-quality stylizations and outperforms existing methods both qualitatively and quantitatively.
Haoyu Ren, Wei Xu, Qing Zhu et al.· International Conference on...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
