Lune

SIGGRAPH2024Top-tier venue

N-Dimensional Gaussians for Fitting of High Dimensional Functions

Stavros Diolatzis, Tobias Zirr, Alexander Kuznetsov, Georgios Kopanas, Anton Kaplanyan

Abstract

In the wake of many new ML-inspired approaches for reconstructing and representing high-quality 3D content, recent hybrid and explicitly learned representations exhibit promising performance and quality characteristics. However, their scaling to higher dimensions is challenging, e.g. when accounting for dynamic content with respect to additional parameters such as material properties, illumination, or time. In this paper, we tackle these challenges for an explicit representations based on Gaussian mixture models. With our solutions, we arrive at efficient fitting of compact N-dimensional Gaussian mixtures and enable efficient evaluation at render time: For fast fitting and evaluation, we introduce a high-dimensional culling scheme that efficiently bounds N-D Gaussians, inspired by Locality Sensitive Hashing. For adaptive refinement yet compact representation, we introduce a loss-adaptive density control scheme that incrementally guides the use of additional capacity towards missing details. With these tools we can for the first time represent complex appearance that depends on many input dimensions beyond position or viewing angle within a compact, explicit representation optimized in minutes and rendered in milliseconds.

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.

10 top-tier papers have cited it since. Know what they found before your reviewers do.

Questions to start from

Lune can draw on

the full paper · the top-tier papers that cite it · related work

Get the answer

Free to start. No credit card required.

Lineage

  • Anti-Aliased 2D Gaussian Splatting cites NeuS: Learning Neural Implicit Surfaces by Volume Rendering for Multi-view Reconstruction
  • Anti-Aliased 2D Gaussian Splatting cites Instant neural graphics primitives with a multiresolution hash encoding
  • Anti-Aliased 2D Gaussian Splatting cites 3D Gaussian Splatting for Real-Time Radiance Field Rendering
  • NeuS: Learning Neural Implicit Surfaces by Volume Rendering for Multi-view Reconstruction cites Fourier Features Let Networks Learn High Frequency Functions in Low Dimensional Domains
  • Orientation-anchored Hyper-Gaussian for 4D Reconstruction from Casual Videos cites 3D Gaussian Splatting for Real-Time Radiance Field Rendering
  • Image-GS: Content-Adaptive Image Representation via 2D Gaussians cites Instant neural graphics primitives with a multiresolution hash encoding
  • Image-GS: Content-Adaptive Image Representation via 2D Gaussians cites Fourier Features Let Networks Learn High Frequency Functions in Low Dimensional Domains
  • Instant neural graphics primitives with a multiresolution hash encoding cites Fourier Features Let Networks Learn High Frequency Functions in Low Dimensional Domains
  • 3D Gaussian Splatting for Real-Time Radiance Field Rendering cites Instant neural graphics primitives with a multiresolution hash encoding
  • DDGS-CT: Direction-Disentangled Gaussian Splatting for Realistic Volume Rendering cites 3D Gaussian Splatting for Real-Time Radiance Field Rendering
  • Universal Beta Splatting cites Instant neural graphics primitives with a multiresolution hash encoding
  • Universal Beta Splatting cites 3D Gaussian Splatting for Real-Time Radiance Field Rendering
Builds onCited byLeft to right by year; the more cited, the higher.

Cited by top-tier papers10

  1. DDGS-CT: Direction-Disentangled Gaussian Splatting for Realistic Volume RenderingZhongpai Gao, Benjamin Planche, Meng Zheng, Xiao Chen et al.NeurIPS 2024 · 34 citations
  2. Image-GS: Content-Adaptive Image Representation via 2D GaussiansYunxiang Zhang, Bingxuan Li, Alexandr Kuznetsov, Akshay Jindal et al.SIGGRAPH 2025 · 12 citations
  3. Anti-Aliased 2D Gaussian SplattingMae Younes, Adnane BoukhaymaNeurIPS 2025 · 9 citations
  4. Orientation-anchored Hyper-Gaussian for 4D Reconstruction from Casual VideosJunyi Wu, Jiachen Tao, Haoxuan Wang, Gaowen Liu et al.NeurIPS 2025 · 9 citations
  5. Universal Beta SplattingRong Liu, Zhongpai Gao, Benjamin Planche, Meida Chen et al.ICLR 2026 · 4 citations

Builds on18

  1. 3D Gaussian Splatting for Real-Time Radiance Field RenderingBernhard Kerbl, Georgios Kopanas, Thomas Leimkühler, George DrettakisSIGGRAPH 2023 · 5,687 citations
  2. Instant neural graphics primitives with a multiresolution hash encodingThomas Müller, Alex Evans, Christoph Schied, Alexander KellerSIGGRAPH 2022 · 4,089 citations
  3. Fourier Features Let Networks Learn High Frequency Functions in Low Dimensional DomainsMatthew Tancik, Pratul P. Srinivasan, Ben Mildenhall, Sara Fridovich-Keil et al.NeurIPS 2020 · 4,036 citations
  4. Reformer: The Efficient TransformerNikita Kitaev, Lukasz Kaiser, Anselm LevskayaICLR 2020 · 2,878 citations
  5. NeuS: Learning Neural Implicit Surfaces by Volume Rendering for Multi-view ReconstructionPeng Wang, Lingjie Liu, Yuan Liu, Christian Theobalt et al.NeurIPS 2021 · 2,500 citations

Related papers

  1. HERA: Hybrid Explicit Representation for Ultra-Realistic Head AvatarsHongrui Cai, Yuting Xiao, Xuan Wang, Jiafei Li et al.CVPR 2025
  2. iLRM: An Iterative Large 3D Reconstruction ModelGyeongjin Kang, Seungtae Nam, Seungkwon Yang, Xiangyu Sun et al.CVPR 2026 · 19 citations
  3. Prune Wisely, Reconstruct Sharply: Compact 3D Gaussian Splatting via Adaptive Pruning and Difference-of-Gaussian PrimitivesHaoran Wang, Guoxi Huang, Fan Zhang, David Bull et al.CVPR 2026 · 6 citations
  4. LIFe-GoM: Generalizable Human Rendering with Learned Iterative Feedback Over Multi-Resolution Gaussians-on-MeshJing Wen, Alexander G. Schwing, Shenlong WangICLR 2025
  5. Animatable 3D Gaussian: Fast and High-Quality Reconstruction of Multiple Human AvatarsYang Liu, Xiang Huang, Minghan Qin, Qinwei Lin et al.ACM MM 2024 · 8 citations
Dusk over the sea between two cliffs drawn in fine vertical lines