Eulerian Gaussian Splatting using Hashed Probability Pyramids
Quick Take
The proposed Eulerian Gaussian Splatting framework enhances 3D Gaussian Splatting by optimizing volumetric probability density through gradient-based methods, achieving state-of-the-art mip-NeRF 360 reconstruction quality while maintaining fast rendering speeds.
Key Points
- Introduces a probabilistic splat-based radiance field framework.
- Utilizes a memory-efficient multi-scale hierarchical grid for optimization.
- Achieves state-of-the-art reconstruction quality on mip-NeRF 360.
- Maintains fast rasterization speeds comparable to 3D Gaussian Splatting.
- Employs an unbiased gradient estimator to reduce optimization variance.
Article Excerpt
From source RSS / original summaryarXiv:2605. 29136v1 Announce Type: new Abstract: We introduce a probabilistic splat-based radiance field framework that retains the fast rasterization and test-time efficiency of 3D Gaussian Splatting (3DGS) while replacing heuristic primitive manipulation with gradient-based optimization of a volumetric probability density. Rather than relocating, splitting, or culling Gaussians via hand-tuned densification (e. g. , ADC), we treat primitive locations as samples drawn from a persistent, learnable density.
We instantiate this density using a novel, memory-efficient multi-scale hierarchical grid that enables end-to-end gradient-based optimization. To stabilize the optimization, we derive an unbiased gradient estimator with control variates that markedly reduces variance. By allowing probability mass to flow to where the loss demands, our framework eliminates brittle priors and naturally explores the volume, achieving state-of-the-art reconstruction quality on mip-NeRF 360 while preserving 3DGS-level rendering speed.
Reader Mode unavailable (could not extract clean content).
Want this in your inbox every morning?
Daily brief at your local 8am — bilingual EN/中文, free.
More from arXiv cs.CV
See more →Evi-Steer: Learning to Steer Biomedical Vision-Language Models through Efficient and Generalizable Evidential Tuning
Evi-Steer introduces a novel evidential tuning framework for BiomedCLIP, achieving 0.11% parameter updates while enhancing uncertainty-aware fine-tuning. It outperforms state-of-the-art methods across 15 biomedical imaging datasets, proving effective in few-shot learning and domain shifts for clinical applications.
