Alias-free 4D Gaussian Splatting
Not on the map. Why?
Abstract (arXiv)
Existing dynamic scene reconstruction methods based on Gaussian Splatting enable real-time rendering and generate realistic images. However, adjusting the camera's focal length or the distance between Gaussian primitives and the camera to modify rendering resolution often introduces strong artifacts, stemming from the frequency constraints of 4D Gaussians and Gaussian scale mismatch induced by the 2D dilated filter. To address this, we derive a maximum sampling frequency formulation for 4D Gaussian Splatting and introduce a 4D scale-adaptive filter and scale loss, which flexibly regulates the sampling frequency of 4D Gaussian Splatting. Our approach eliminates high-frequency artifacts under increased rendering frequencies while effectively reducing redundant Gaussians in multi-view video reconstruction. We validate the proposed method through monocular and multi-view video reconstruction experiments.Ours project page: https://4d-alias-free.github.io/4D-Alias-free/
Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 30 of its 51 references that are in the map. First posted on arXiv 23 Nov 2025.
Builds on
30 of 51 references.
References · 30
- 20233D Gaussian Splatting for Real-Time Radiance Field Renderingcited by 6,141
- 2021Mip-NeRF: A Multiscale Representation for Anti-Aliasing Neural Radiance Fieldscited by 1,957
- 20234D Gaussian Splatting for Real-Time Dynamic Scene Renderingcited by 1,144
- 2023Deformable 3D Gaussians for High-Fidelity Monocular Dynamic Scene Reconstructioncited by 753
- 2020Neural Scene Flow Fields for Space-Time View Synthesis of Dynamic Scenescited by 750
- 2023K-Planes: Explicit Radiance Fields in Space, Time, and Appearancecited by 742
- 2023Zip-NeRF: Anti-Aliased Grid-Based Neural Radiance Fieldscited by 667
- 2023Mip-Splatting: Alias-free 3D Gaussian Splattingcited by 661
- 2023Real-time Photorealistic Dynamic Scene Representation and Rendering with 4D Gaussian Splattingcited by 470
- 2022Fast Dynamic Radiance Fields with Time-Aware Neural Voxelscited by 344
- 2023Spacetime Gaussian Feature Splatting for Real-Time Dynamic View Synthesiscited by 341
- 2023SC-GS: Sparse-Controlled Gaussian Splatting for Editable Dynamic Scenescited by 339
18 more
- 2023GS-SLAM: Dense Visual SLAM with 3D Gaussian Splattingcited by 278
- 2023GaussianShader: 3D Gaussian Splatting with Shading Functions for Reflective Surfacescited by 249
- 2022Tensor4D : Efficient Neural 4D Decomposition for High-fidelity Dynamic Reconstruction and Renderingcited by 217
- 2023HyperReel: High-Fidelity 6-DoF Video with Ray-Conditioned Samplingcited by 173
- 2023Tri-MipRF: Tri-Mip Representation for Efficient Anti-Aliasing Neural Radiance Fieldscited by 142
- 2024Per-Gaussian Embedding-Based Deformation for Deformable 3D Gaussian Splattingcited by 104
- 2023SWinGS: Sliding Windows for Dynamic 3D Gaussian Splattingcited by 46
- 20243D-HGS: 3D Half-Gaussian Splattingcited by 43
- 2024SA-GS: Scale-Adaptive Gaussian Splatting for Training-Free Anti-Aliasingcited by 40
- 2024Spectrally Pruned Gaussian Fields with Neural Compensationcited by 33
- 2024DN-4DGS: Denoised Deformable Network with Temporal-Spatial Aggregation for Dynamic Scene Renderingcited by 28
- 2024Rip-NeRF: Anti-aliasing Radiance Fields with Ripmap-Encoded Platonic Solidscited by 23
- 2023NeRRF: 3D Reconstruction and View Synthesis for Transparent and Specular Objects with Neural Refractive-Reflective Fieldscited by 16
- 2023Implicit Event-RGBD Neural SLAMcited by 16
- 2023SlimmeRF: Slimmable Radiance Fieldscited by 15
- 2025PartRM: Modeling Part-Level Dynamics with Large Cross-State Reconstruction Modelcited by 15
- 2025Unifying Appearance Codes and Bilateral Grids for Driving Scene Gaussian Splattingcited by 14
- 2024Mipmap-GS: Let Gaussians Deform with Scale-specific Mipmap for Anti-aliasing Renderingcited by 9
Built on by
Citing papers per year: 2025: 1; 2026: 1.
2 papers.