Budgeted-GS is a post‑hoc technique that transforms any trained 3D Gaussian Splatting model into a factoring tree—a multi‑resolution hierarchy of moment‑matched aggregates. After a brief construction pass, a single quality parameter selects the appropriate level of detail for each view, allowing the same city‑scale model to run in real time on GPUs with varying memory capacities. The method also informs budget‑centered training, enabling models to be built directly at the necessary size and avoiding wasted optimization of later discarded primitives.
By Haipeng Wang
arXiv:2607. 17842v1 Announce Type: cross Abstract: Recent breakthroughs in 3D Gaussian Splatting (3DGS) have advanced neural rendering with high fidelity and speed.
By Tingjia Zhang, Bo Chen, Shengzhong Liu, Fan Wu, Guihai Chen
ReSplat introduces a recurrent Gaussian splatting model that iteratively refines 3D Gaussians using the rendering error as a feedback signal, avoiding explicit gradient computation. The method starts from a compact reconstruction in a subsampled space, producing far fewer Gaussians than prior per‑pixel models, which reduces computational cost. Experiments on multiple datasets, view counts, and resolutions show state‑of‑the‑art performance with faster rendering speeds.
By Haofei Xu, Daniel Barath, Andreas Geiger, Marc Pollefeys
Gauss What You Need: Compact Gaussian Splatting Across Scene Scales introduces TangoGS, a method that automatically selects the number of Gaussian primitives for 3D Gaussian Splatting by combining capture-derived model sizing with training-based adaptation. The approach first estimates a learning allowance based on the capture’s total pixels, then adjusts the number of Gaussians during training according to reconstruction quality. On standard benchmarks, TangoGS matches the best baseline’s PSNR while using 48% fewer Gaussians, and on larger captures it scales automatically to achieve the highest mean PSNR with 2.3× more Gaussians.
By Afif Boudaoud, Jiayi Liu, Alexandru Calotoiu, Torsten Hoefler
arXiv:2611.05593v1 Announce Type: cross
Abstract: Can a neural network learn to render 3D Gaussian splats on its own, with no rasterizer in the renderer? We present GaussianRenderFormer, a transforme...
By Shahaf Valencia Levy, Sagie Benaim
TileSkipper introduces a region‑adaptive tile pruning strategy for 3D Gaussian splatting rasterizers, assigning a static per‑Gaussian contribution cutoff policy that is calibrated on a frozen checkpoint. The method partitions Gaussians into 64 groups, uses a single‑byte policy per Gaussian, and requires no runtime updates or additional kernels. Across 13 benchmark scenes, TileSkipper achieves up to 1.238× speedups with negligible PSNR loss, and integrates with existing opacity‑aware bounds for further compiler‑only gains.
By Jingxing Li, Yongjae Lee, Deliang Fan, Abhay Kumar Yadav, Cheng Peng, Rama Chellappa
arXiv:2610.28615v1 Announce Type: new
Abstract: Deploying a trained 3D Gaussian Splatting scene under shrinking compute budgets requires one primitive set to remain effective when rendered at smaller...
By Radu Beche, Raoul de Charette
arXiv:2609.06157v1 Announce Type: cross
Abstract: 3D Gaussian splatting (3DGS) represents scenes with explicit primitives and supports real-time novel-view synthesis, yet its system efficiency varies...
By Minnan Pei, Qiwei Dong, Yihan Zhou, Gang Li, Yuchen Zhu, Wenju Zhao, Zhongtian Long, Siting Wang, Peisong Wang, Jian Cheng
arXiv:2609.39553v1 Announce Type: new
Abstract: 3D Gaussian Splatting (3DGS) enables real-time novel view synthesis, but existing general-purpose acceleration methods suffer severe rendering quality...
By Changbai Li, Shuo Yang, Yichen Yang, Shuwei Shao, Huobin Tan
3D Gaussian Splatting (3DGS) enables real-time novel view synthesis, but existing general-purpose acceleration methods suffer severe rendering quality degradation when extended to more complex, large-...
LoBE-GS is a Load‑Balanced and Efficient 3D Gaussian Splatting framework designed for large‑scale scene reconstruction. It introduces a load‑balanced KD‑tree partitioning scheme that balances camera counts per block, uses depth‑based back‑projection to speed up camera assignment, and applies visibility cropping and selective densification to cut training costs. Experiments on urban and outdoor datasets show up to an order‑of‑magnitude faster scene‑partitioning and a 3.2× reduction in worst‑block fine‑training time compared to CityGaussian, while keeping reconstruction quality competitive.
By Sheng-Hsiang Hung, Ting-Yu Yen, Wei-Fang Sun, Simon See, Shih-Hsuan Hung, Hung-Kuo Chu
arXiv:2610.07958v1 Announce Type: new
Abstract: Feed-forward 3D Gaussian Splatting (3DGS) reconstructs a scene in a single forward pass, replacing per-scene optimization with a network trained across...
By Minhyeok Lee, Jungho Lee, Minseok Kang, Heeseung Choi, Ig-Jae Kim, Sangyoun Lee