arXiv AI
Jul 3
Learning 3D-Gaussian Simulators from RGB Videos
arXiv:2503. 24009v3 Announce Type: replace-cross Abstract: Realistic simulation is critical for applications ranging from robotics to animation.
VersaGauss: A Versatile Framework for Generating Multiphase Dynamics with 3D Gaussians
VersaGauss is a unified framework that generates, simulates, and renders 3D dynamic scenes using 3D Gaussians, supporting multiphase interactions among materials such as fluid, rubber, sand, and snow. It takes a few input images and produces realistic, physics-driven scenes, employing a particle pruning algorithm to optimize Gaussian kernel distribution and a Coupled Multiphase Point Method (CMPM) for modeling multiphase dynamics. The framework also introduces harmonic interpolation within CMPM and a Gaussian evolution strategy to achieve realistic fluid rendering, with extensive experiments validating its performance.
Related stories
arXiv Computer Vision
Aug 25
LagrangeGS: Non-Conservative Lagrangian System on Dynamic 3D Gaussian Splatting
arXiv:2608.22773v1 Announce Type: new Abstract: Dynamic 3D Gaussian Splatting (3DGS) achieves photorealistic reconstruction of time-varying scenes, and recent physics-aware extensions improve extrapo...
arXiv AI
Sep 10
PhysMAS: Physics-Grounded Multi-Agent Synthesis of Compositional 4D Gaussians
arXiv:2609.07174v1 Announce Type: new Abstract: Efficient, fully automatic, and physically plausible 4D Gaussian synthesis is an important goal for dynamic scene generation. Recent physics-based meth...
arXiv AI
Sep 4
TruncGradGS: Improved 3D Gaussian Splatting via Truncated Gradient Updates
The paper introduces TruncGradGS, a piecewise truncated gradient approach that mitigates gradient vanishing in 3D Gaussian Splatting, enhancing optimization stability and robustness to initializations. It demonstrates consistent improvements over random and COLMAP initializations in both static and dynamic settings. Additionally, the authors highlight limitations of existing dynamic scene benchmarks and present a new synthetic dataset for evaluating dynamic Gaussian Splatting.
arXiv Computer Vision
Sep 2
NanoGS: Training-Free Gaussian Splat Simplification
arXiv:2603.16103v3 Announce Type: replace Abstract: 3D Gaussian Splat (3DGS) enables high-fidelity, real-time novel view synthesis by representing scenes with large sets of anisotropic primitives, bu...
arXiv Computer Vision
1d ago
GARO: Geometry-Aware Redundancy Optimization for Real-Time and High-Fidelity Dynamic Gaussian Splatting
arXiv:2609.23509v1 Announce Type: new Abstract: Novel view synthesis is a key task for dynamic scene reconstruction, where high rendering speed is essential for applications such as virtual reality....
arXiv Computer Vision
Sep 14
SUCCESS-GS: Survey of Compactness and Compression for Efficient Static and Dynamic Gaussian Splatting
arXiv:2512.07197v2 Announce Type: replace Abstract: 3D Gaussian Splatting (3DGS) has emerged as a powerful explicit representation enabling real-time, high-fidelity 3D reconstruction and novel view s...
arXiv Machine Learning
Jul 28
Meshless Domain Randomization via Explicit Parameter Perturbation of 3D Gaussian Splatting
arXiv:2607. 22890v1 Announce Type: cross Abstract: Domain Randomization (DR) is a standard technique for closing the Sim-to-Real gap, yet traditional DR pipelines rely on classical computer graphics rendering driven by polygon meshes.
arXiv AI
Jun 24
Inclusive Interactive Collisions for Multi-View Consistent Compositional 3D Generation
arXiv:2606. 24206v1 Announce Type: cross Abstract: Recent breakthroughs in 3D generation have advanced notably with the development of text-to-image diffusion model.
arXiv Computer Vision
Sep 4
F4Splat: Feed-Forward Predictive Densification for Feed-Forward 3D Gaussian Splatting
F4Splat introduces a feed‑forward predictive densification strategy for 3D Gaussian splatting that allocates Gaussians based on a densification‑score guided by spatial complexity and multi‑view overlap. The method predicts per‑region scores to estimate required Gaussian density, enabling explicit control over the total Gaussian budget without retraining. This adaptive allocation reduces redundancy in simple regions and minimizes duplicate Gaussians across overlapping views, yielding compact yet high‑quality 3D representations and superior novel‑view synthesis performance with fewer Gaussians.
arXiv Machine Learning
Sep 16
3D Field Data Reduction with Adaptive Sample-Based Gaussian-Encoded Reconstruction
The paper introduces a unified sample‑based Gaussian encoding method that represents structured grids, unstructured meshes, and particle data under a single fixed‑budget formulation. By initializing and refining Gaussian primitives directly from input samples while maintaining a prescribed primitive count, the method achieves higher reconstruction accuracy with fewer primitives—up to 4.8 dB higher PSNR and roughly a 44× reduction in primitive count compared to prior approaches. For time‑varying data, warm‑starting from the previous timestep further reduces optimization effort while preserving reconstruction quality.
arXiv Computer Vision
5d ago
SplashSplat: Reconstructing Splashing Liquids from Real-World Multi-View Videos
SplashSplat introduces a new benchmark of 20 real-world splashing liquid scenes captured with seven synchronized 4K cameras at 60 fps, providing per-view liquid and container masks and fixed evaluation splits. The method reconstructs per‑frame liquid signed distance fields (SDFs) from these masks, fuses them into a coarse velocity field, and uses Lagrangian carriers to generate differentiable local Gaussian representations for rendering. SplashSplat outperforms existing dynamic Gaussian splatting techniques on both real and synthetic data, offering more physically plausible motion, lower training cost, and enabling temporal interpolation and style transfer without re‑optimization.