Turbo-GS: Accelerating 3D Gaussian Fitting for High-Resolution Radiance Fields
Ankit Dhiman, Tao Lu, R. Srinath, Emre Arslan, Angela Xing, Yuanbo Xiangli, Venkatesh Babu Radhakrishnan, Srinath Sridhar
Abstract
gs Figure 1. Turbo-GS accelerates 3DGS fitting significantly while preserving rendering quality. It proposes an efficient densification strategy and innovative dilated rendering that allow training on 4K images in minutes, significantly outperforming baseline methods. Notably, Turbo-GS converges on the 4K bicycle scene in just 13 minutes-over 3× faster than Taming 3DGS (40 minutes), 14× faster than 3DGS (187 minutes) and Scaffold-GS (185 minutes).
Ask Lune
Know this paper in minutes, not an afternoon.
Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.
9 top-tier papers have cited it since. Know what they found before your reviewers do.
Lune can draw on
the full paper · the top-tier papers that cite it · related work
Free to start. No credit card required.
Lineage
- iLRM: An Iterative Large 3D Reconstruction Model cites 3D Gaussian Splatting for Real-Time Radiance Field Rendering
- iLRM: An Iterative Large 3D Reconstruction Model cites Mip-NeRF 360: Unbounded Anti-Aliased Neural Radiance Fields
- 3DGS-LM: Faster Gaussian-Splatting Optimization with Levenberg-Marquardt cites Instant neural graphics primitives with a multiresolution hash encoding
- 3DGS-LM: Faster Gaussian-Splatting Optimization with Levenberg-Marquardt cites 3D Gaussian Splatting for Real-Time Radiance Field Rendering
- 3DGS-LM: Faster Gaussian-Splatting Optimization with Levenberg-Marquardt cites Mip-NeRF 360: Unbounded Anti-Aliased Neural Radiance Fields
- 3DGS-LM: Faster Gaussian-Splatting Optimization with Levenberg-Marquardt cites Plenoxels: Radiance Fields without Neural Networks
- ContraGS: Codebook-Condensed and Trainable Gaussian Splatting for Fast, Memory-Efficient Reconstruction cites 3DGS-LM: Faster Gaussian-Splatting Optimization with Levenberg-Marquardt
- ContraGS: Codebook-Condensed and Trainable Gaussian Splatting for Fast, Memory-Efficient Reconstruction cites 3D Gaussian Splatting for Real-Time Radiance Field Rendering
- ContraGS: Codebook-Condensed and Trainable Gaussian Splatting for Fast, Memory-Efficient Reconstruction cites Mip-NeRF 360: Unbounded Anti-Aliased Neural Radiance Fields
- FlexGaussian: Flexible and Cost-Effective Training-Free Compression for 3D Gaussian Splatting cites Instant neural graphics primitives with a multiresolution hash encoding
- FlexGaussian: Flexible and Cost-Effective Training-Free Compression for 3D Gaussian Splatting cites 3D Gaussian Splatting for Real-Time Radiance Field Rendering
- FlexGaussian: Flexible and Cost-Effective Training-Free Compression for 3D Gaussian Splatting cites Mip-NeRF 360: Unbounded Anti-Aliased Neural Radiance Fields
- 3D Gaussian Splatting for Real-Time Radiance Field Rendering cites PlenOctrees for Real-time Rendering of Neural Radiance Fields
- 3D Gaussian Splatting for Real-Time Radiance Field Rendering cites Instant neural graphics primitives with a multiresolution hash encoding
- 3D Gaussian Splatting for Real-Time Radiance Field Rendering cites Plenoxels: Radiance Fields without Neural Networks
- Mip-NeRF 360: Unbounded Anti-Aliased Neural Radiance Fields cites PlenOctrees for Real-time Rendering of Neural Radiance Fields
- RoboPearls: Editable Video Simulation for Robot Manipulation cites 3D Gaussian Splatting for Real-Time Radiance Field Rendering
- Plenoxels: Radiance Fields without Neural Networks cites PlenOctrees for Real-time Rendering of Neural Radiance Fields
Cited by top-tier papers9
- iLRM: An Iterative Large 3D Reconstruction ModelGyeongjin Kang, Seungtae Nam, Seungkwon Yang, Xiangyu Sun et al.CVPR 2026 · 19 citations
- 3DGS-LM: Faster Gaussian-Splatting Optimization with Levenberg-MarquardtLukas Höllein, Aljaz Bozic, Michael Zollhöfer, Matthias NießnerICCV 2025 · 10 citations
- ContraGS: Codebook-Condensed and Trainable Gaussian Splatting for Fast, Memory-Efficient ReconstructionSankeerth Durvasula, Sharanshangar Muhunthan, Zain Moustafa, Richard Chen et al.ICCV 2025 · 6 citations
- RoboPearls: Editable Video Simulation for Robot ManipulationTang Tao, Likui Zhang, Youpeng Wen, Kaidong Zhang et al.ICCV 2025 · 4 citations
- FlexGaussian: Flexible and Cost-Effective Training-Free Compression for 3D Gaussian SplattingBoyuan Tian, Qizhe Gao, Siran Xianyu, Xiaotong Cui et al.ACM MM 2025 · 2 citations
Builds on25
- 3D Gaussian Splatting for Real-Time Radiance Field RenderingBernhard Kerbl, Georgios Kopanas, Thomas Leimkühler, George DrettakisSIGGRAPH 2023 · 5,687 citations
- Instant neural graphics primitives with a multiresolution hash encodingThomas Müller, Alex Evans, Christoph Schied, Alexander KellerSIGGRAPH 2022 · 4,089 citations
- Mip-NeRF 360: Unbounded Anti-Aliased Neural Radiance FieldsJonathan T. Barron, Ben Mildenhall, Dor Verbin, Pratul P. Srinivasan et al.CVPR 2022 · 1,603 citations
- PlenOctrees for Real-time Rendering of Neural Radiance FieldsAlex Yu, Ruilong Li, Matthew Tancik, Hao Li et al.ICCV 2021 · 1,284 citations
- Plenoxels: Radiance Fields without Neural NetworksSara Fridovich-Keil, Alex Yu, Matthew Tancik, Qinhong Chen et al.CVPR 2022 · 1,237 citations
Related papers
- Improving Densification in 3D Gaussian Splatting for High-Fidelity RenderingXiaobin Deng, Changyu Diao, Min Li, Ruohan Yu, Duanqing XuCVPR Findings 2026
- Speedy-Splat: Fast 3D Gaussian Splatting with Sparse Pixels and Sparse PrimitivesAlex Hanson, Allen Tu, Geng Lin, Vasu Singla et al.CVPR 2025
- Faster-GS: Analyzing and Improving Gaussian Splatting OptimizationFlorian Hahlbohm, Linus Franke, Martin Eisemann, Marcus A. MagnorCVPR 2026 · 16 citations
- DashGaussian: Optimizing 3D Gaussian Splatting in 200 SecondsYouyu Chen, Junjun Jiang, Kui Jiang, Xiao Tang et al.CVPR 2025
- Compact 3D Gaussian Representation for Radiance FieldJoo Chan Lee, Daniel Rho, Xiangyu Sun, Jong Hwan Ko et al.CVPR 2024
