SplatCo: Structure-View Collaborative Gaussian Splatting for Detail-Preserving Rendering of Large-Scale Unbounded Scenes
Not on the map. Why?
Abstract (arXiv)
We present SplatCo, a structure-view collaborative Gaussian splatting framework for high-fidelity rendering of complex outdoor scenes. SplatCo builds upon three novel components: 1) a cross-structure collaboration module that combines global tri-plane representations, which capture coarse scene layouts, with local context grid features representing fine details. This fusion is achieved through a hierarchical compensation mechanism, ensuring both global spatial awareness and local detail preservation; 2) a cross-view pruning mechanism that removes overfitted or inaccurate Gaussians based on structural consistency, thereby improving storage efficiency and preventing rendering artifacts; 3) a structure view co-learning module that aggregates structural gradients with view gradients,thereby steering the optimization of Gaussian geometric and appearance attributes more robustly. By combining these key components, SplatCo effectively achieves high-fidelity rendering for large-scale scenes. Code and project page are available at https://splatco-tech.github.io.
Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 61 of its 84 references that are in the map. First posted on arXiv 23 May 2025.
Builds on
61 of 84 references.
References · 61
- 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,177
- 20233D Gaussian Splatting for Real-Time Radiance Field Renderingcited by 6,226
- 2022Instant Neural Graphics Primitives with a Multiresolution Hash Encodingcited by 3,723
- 2018CBAM: Convolutional Block Attention Modulecited by 2,477
- 2021Mip-NeRF 360: Unbounded Anti-Aliased Neural Radiance Fieldscited by 2,032
- 2021Mip-NeRF: A Multiscale Representation for Anti-Aliasing Neural Radiance Fieldscited by 1,964
- 2021Plenoxels: Radiance Fields without Neural Networkscited by 1,613
- 2023DUSt3R: Geometric 3D Vision Made Easycited by 1,567
- 2020D-NeRF: Neural Radiance Fields for Dynamic Scenescited by 1,465
- 2020NeRF in the Wild: Neural Radiance Fields for Unconstrained Photo Collectionscited by 1,232
- 2024Grounding Image Matching in 3D with MASt3Rcited by 983
- 2018MVSNet: Depth Inference for Unstructured Multi-view Stereocited by 788
38 more
- 2023K-Planes: Explicit Radiance Fields in Space, Time, and Appearancecited by 746
- 2023Scaffold-GS: Structured 3D Gaussians for View-Adaptive Renderingcited by 695
- 2019Cascade Cost Volume for High-Resolution Multi-View Stereo and Stereo Matchingcited by 417
- 2021Mega-NeRF: Scalable Construction of Large-Scale NeRFs for Virtual Fly-Throughscited by 398
- 2023Compact 3D Gaussian Representation for Radiance Fieldcited by 372
- 2025Fast3R: Towards 3D Reconstruction of 1000+ Images in One Forward Passcited by 367
- 2023Triplane Meets Gaussian Splatting: Fast and Generalizable Single-View 3D Reconstruction with Transformerscited by 258
- 2019Recurrent MVSNet for High-resolution Multi-view Stereo Depth Inferencecited by 254
- 2024Octree-GS: Towards Consistent Real-time Rendering with LOD-Structured 3D Gaussianscited by 230
- 2024A Survey on 3D Gaussian Splattingcited by 224
- 2024A Hierarchical 3D Gaussian Representation for Real-Time Rendering of Very Large Datasetscited by 216
- 2024VastGaussian: Vast 3D Gaussians for Large Scene Reconstructioncited by 209
- 2024CityGaussian: Real-time High-quality Large-Scale Scene Rendering with Gaussianscited by 192
- 2023MatrixCity: A Large-scale City Dataset for City-scale Neural Rendering and Beyondcited by 185
- 2021Deblur-NeRF: Neural Radiance Fields from Blurry Imagescited by 179
- 2021Embodied Intelligence via Learning and Evolutioncited by 163
- 2019Liquid Warping GAN: A Unified Framework for Human Motion Imitation, Appearance Transfer and Novel View Synthesiscited by 161
- 2022VoxGRAF: Fast 3D-Aware Image Synthesis with Sparse Voxel Gridscited by 133
- 2024Recent Advances in 3D Gaussian Splattingcited by 131
- 2021TransMVSNet: Global Context-aware Multi-view Stereo Network with Transformerscited by 117
- 2024Pixel-GS: Density Control with Pixel-aware Gradient for 3D Gaussian Splattingcited by 113
- 20243D Gaussian as a New Era: A Surveycited by 104
- 2024ContextGS: Compact 3D Gaussian Splatting with Anchor Level Context Modelcited by 102
- 2023NerfAcc: Efficient Sampling Accelerates NeRFscited by 90
- 2024GSDF: 3DGS Meets SDF for Improved Rendering and Reconstructioncited by 83
- 2024GaMeS: Mesh-Based Adapting and Modification of Gaussian Splattingcited by 70
- 2016SIFT Meets CNN: A Decade Survey of Instance Retrievalcited by 67
- 2024DOGS: Distributed-Oriented Gaussian Splatting for Large-Scale 3D Reconstruction Via Gaussian Consensuscited by 51
- 2022MVSTER: Epipolar Transformer for Efficient Multi-View Stereocited by 50
- 2023Globally Consistent Normal Orientation for Point Clouds by Regularizing the Winding-Number Fieldcited by 37
- 2024AniGS: Animatable Gaussian Avatar from a Single Image with Inconsistent Gaussian Reconstructioncited by 36
- 2022Iterative Poisson Surface Reconstruction (iPSR) for Unoriented Pointscited by 31
- 2023SHACIRA: Scalable HAsh-grid Compression for Implicit Neural Representationscited by 31
- 2024GaussianRoom: Improving 3D Gaussian Splatting with SDF Guidance and Monocular Cues for Indoor Scene Reconstructioncited by 31
- 2020A Novel Recurrent Encoder-Decoder Structure for Large-Scale Multi-view Stereo Reconstruction from An Open Aerial Datasetcited by 28
- 2025CityGS-X: A Scalable Architecture for Efficient and Geometrically Accurate Large-Scale Scene Reconstructioncited by 26
- 2023VMesh: Hybrid Volume-Mesh Representation for Efficient View Synthesiscited by 25
- 2024Implicit Gaussian Splatting with Efficient Multi-Level Tri-Plane Representationcited by 21
50 most cited of 61 All 61 (JSON)
Built on by
Citing papers per year: 2026: 1.
1 paper.