mlsanityData to 7 Oct 2026

GPS-Gaussian: Generalizable Pixel-wise 3D Gaussian Splatting for Real-time Human Novel View Synthesis

arXiv 2312.02155 ↗First posted 4 Dec 2023cs.CVcited by 170

Not on the map. Why?

Abstract (arXiv)

We present a new approach, termed GPS-Gaussian, for synthesizing novel views of a character in a real-time manner. The proposed method enables 2K-resolution rendering under a sparse-view camera setting. Unlike the original Gaussian Splatting or neural implicit rendering methods that necessitate per-subject optimizations, we introduce Gaussian parameter maps defined on the source views and regress directly Gaussian Splatting properties for instant novel view synthesis without any fine-tuning or optimization. To this end, we train our Gaussian parameter regression module on a large amount of human scan data, jointly with a depth estimation module to lift 2D parameter maps to 3D space. The proposed framework is fully differentiable and experiments on several datasets demonstrate that our method outperforms state-of-the-art methods while achieving an exceeding rendering speed.

Key facts. Cited by 170 papers in the map (data through 7 Oct 2026). Builds on 52 of its 77 references that are in the map. First posted on arXiv 4 Dec 2023.

Builds on

52 of 77 references.

References · 52

  1. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,029
  2. 20233D Gaussian Splatting for Real-Time Radiance Field Renderingcited by 6,141
  3. 2022Instant Neural Graphics Primitives with a Multiresolution Hash Encodingcited by 3,698
  4. 2019DeepSDF: Learning Continuous Signed Distance Functions for Shape Representationcited by 2,682
  5. 2020RAFT: Recurrent All-Pairs Field Transforms for Optical Flowcited by 2,385
  6. 2018Occupancy Networks: Learning 3D Reconstruction in Function Spacecited by 2,037
  7. 2021NeuS: Learning Neural Implicit Surfaces by Volume Rendering for Multi-view Reconstructioncited by 1,701
  8. 2021Plenoxels: Radiance Fields without Neural Networkscited by 1,607
  9. 2020pixelNeRF: Neural Radiance Fields from One or Few Imagescited by 1,574
  10. 2021PlenOctrees for Real-time Rendering of Neural Radiance Fieldscited by 904
  11. 2019PIFu: Pixel-Aligned Implicit Function for High-Resolution Clothed Human Digitizationcited by 818
  12. 2021MVSNeRF: Fast Generalizable Radiance Field Reconstruction from Multi-View Stereocited by 735
38 more
  1. 2023Dynamic 3D Gaussians: Tracking by Persistent Dynamic View Synthesiscited by 731
  2. 2020Neural Body: Implicit Neural Representations with Structured Latent Codes for Novel View Synthesis of Dynamic Humanscited by 634
  3. 2020PIFuHD: Multi-Level Pixel-Aligned Implicit Function for High-Resolution 3D Human Digitizationcited by 521
  4. 2022Point-NeRF: Point-based Neural Radiance Fieldscited by 503
  5. 2022HumanNeRF: Free-viewpoint Rendering of Moving People from Monocular Videocited by 483
  6. 2019SynSin: End-to-end View Synthesis from a Single Imagecited by 364
  7. 2021Extracting Triangular 3D Models, Materials, and Lighting From Imagescited by 363
  8. 2021RAFT-Stereo: Multilevel Recurrent Field Transforms for Stereo Matchingcited by 348
  9. 2019Neural Point-Based Graphicscited by 326
  10. 2022NeuS2: Fast Learning of Neural Implicit Surfaces for Multi-view Reconstructioncited by 311
  11. 2021ICON: Implicit Clothed humans Obtained from Normalscited by 283
  12. 2021Function4D: Real-time Human Volumetric Capture from Very Sparse Consumer RGBD Sensorscited by 246
  13. 2022NeuMan: Neural Human Radiance Field from a Single Videocited by 244
  14. 2019Differentiable Surface Splatting for Point-based Geometry Processingcited by 238
  15. 2020PaMIR: Parametric Model-Conditioned Implicit Representation for Image-based Human Reconstructioncited by 231
  16. 2020Free View Synthesiscited by 231
  17. 2022Tensor4D : Efficient Neural 4D Decomposition for High-fidelity Dynamic Reconstruction and Renderingcited by 217
  18. 2021Shape As Points: A Differentiable Poisson Solvercited by 186
  19. 2022PointAvatar: Deformable Point-based Head Avatars from Videoscited by 183
  20. 2020Stable View Synthesiscited by 165
  21. 2021Neural Human Performer: Learning Generalizable Radiance Fields for Human Performance Renderingcited by 158
  22. 2021CFNet: Cascade and Fused Cost Volume for Robust Stereo Matchingcited by 153
  23. 2021Efficient Neural Radiance Fields for Interactive Free-viewpoint Videocited by 150
  24. 2023Vid2Avatar: 3D Avatar Reconstruction from Videos in the Wild via Self-supervised Scene Decompositioncited by 134
  25. 2019Neural Rerendering in the Wildcited by 121
  26. 2021HumanNeRF: Efficiently Generated Human Radiance Field from Sparse Inputscited by 112
  27. 2021The Power of Points for Modeling Humans in Clothingcited by 90
  28. 2023NerfAcc: Efficient Sampling Accelerates NeRFscited by 90
  29. 2023Neural Point Catacaustics for Novel-View Synthesis of Reflectionscited by 81
  30. 2022KeypointNeRF: Generalizing Image-based Volumetric Avatars using Relative Spatial Encoding of Keypointscited by 77
  31. 2019Revealing Scenes by Inverting Structure from Motion Reconstructionscited by 66
  32. 2021DoubleField: Bridging the Neural Surface and Radiance Fields for High-fidelity Human Reconstruction and Renderingcited by 52
  33. 2022Learning Implicit Templates for Point-Based Clothed Human Modelingcited by 50
  34. 2022FWD: Real-time Novel View Synthesis with Forward Warping and Depthcited by 39
  35. 2021StereoPIFu: Depth Aware Clothed Human Digitization via Stereo Visioncited by 38
  36. 2023NPC: Neural Point Characters from Videocited by 26
  37. 2023GM-NeRF: Learning Generalizable Model-based Neural Radiance Fields from Multi-view Imagescited by 24
  38. 2023CloSET: Modeling Clothed Humans on Continuous Surface with Explicit Template Decompositioncited by 21

50 most cited of 52 All 52 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 1; 2024: 55; 2025: 75; 2026: 39.

170 papers.

Sort:

By area:

  1. 2024MVSplat: Efficient 3D Gaussian Splatting from Sparse Multi-View Imagescited by 553
  2. 2024No Pose, No Problem: Surprisingly Simple 3D Gaussian Splats from Sparse Unposed Imagescited by 241
  3. 2024Octree-GS: Towards Consistent Real-time Rendering with LOD-Structured 3D Gaussianscited by 225
  4. 2024A Survey on 3D Gaussian Splattingcited by 221
  5. 2024Splatt3R: Zero-shot Gaussian Splatting from Uncalibrated Image Pairscited by 171
  6. 2025Streaming 4D Visual Geometry Transformercited by 147
  7. 2024Recent Advances in 3D Gaussian Splattingcited by 130
  8. 2024RadSplat: Radiance Field-Informed Gaussian Splatting for Robust Real-Time Rendering with 900+ FPScited by 110
  9. 2024ManiGaussian: Dynamic Gaussian Splatting for Multi-task Robotic Manipulationcited by 106
  10. 20243D Gaussian as a New Era: A Surveycited by 102
  11. 2024FreeSplat: Generalizable 3D Gaussian Splatting Towards Free-View Synthesis of Indoor Scenescited by 86
  12. 20243D Gaussian Splatting: Survey, Technologies, Challenges, and Opportunitiescited by 77
38 more
  1. 2024Spec-Gaussian: Anisotropic View-Dependent Appearance for 3D Gaussian Splattingcited by 73
  2. 2024Analytic-Splatting: Anti-Aliased 3D Gaussian Splatting via Analytic Integrationcited by 66
  3. 2024HumanSplat: Generalizable Single-Image Human Gaussian Splatting with Structure Priorscited by 54
  4. 2026InfiniteVGGT: Visual Geometry Grounded Transformer for Endless Streamscited by 51
  5. 2024GaussianOcc: Fully Self-supervised and Efficient 3D Occupancy Estimation with Gaussian Splattingcited by 50
  6. 2024GaussTR: Foundation Model-Aligned Gaussian Transformer for Self-Supervised 3D Spatial Understandingcited by 46
  7. 2024Generative Gaussian Splatting for Unbounded 3D City Generationcited by 43
  8. 2024Gaussian Splatting: 3D Reconstruction and Novel View Synthesis, a Reviewcited by 40
  9. 2024Generalizable Human Gaussians for Sparse View Synthesiscited by 40
  10. 2025GWM: Towards Scalable Gaussian World Models for Robotic Manipulationcited by 37
  11. 2023HHAvatar: Gaussian Head Avatar with Dynamic Hairscited by 35
  12. 2025Instant Gaussian Stream: Fast and Generalizable Streaming of Dynamic Scene Reconstruction via Gaussian Splattingcited by 35
  13. 2025Vid2Avatar-Pro: Authentic Avatar from Videos in the Wild via Universal Priorcited by 31
  14. 2024HAHA: Highly Articulated Gaussian Human Avatars with Textured Mesh Priorcited by 30
  15. 2024Generalizable Human Gaussians from Single-View Imagecited by 29
  16. 2024LM-Gaussian: Boost Sparse-view 3D Gaussian Splatting with Large Model Priorscited by 25
  17. 2025Gaussian Graph Network: Learning Efficient and Generalizable Gaussian Representations from Multi-view Imagescited by 25
  18. 2025GaussianFlowOcc: Sparse and Weakly Supervised Occupancy Estimation using Gaussian Splatting and Temporal Flowcited by 24
  19. 2025Advances in Feed-Forward 3D Reconstruction and View Synthesis: A Surveycited by 23
  20. 2025GUAVA: Generalizable Upper Body 3D Gaussian Avatarcited by 22
  21. 2024Gaussian Eigen Models for Human Headscited by 21
  22. 2024EvGGS: A Collaborative Learning Framework for Event-based Generalizable Gaussian Splattingcited by 20
  23. 2025GAS: Generative Avatar Synthesis from a Single Imagecited by 19
  24. 2024PixelGaussian: Generalizable 3D Gaussian Reconstruction from Arbitrary Viewscited by 18
  25. 2024Epipolar-Free 3D Gaussian Splatting for Generalizable Novel View Synthesiscited by 18
  26. 2024Generative Densification: Learning to Densify Gaussians for High-Fidelity Generalizable 3D Reconstructioncited by 18
  27. 2025iLRM: An Iterative Large 3D Reconstruction Modelcited by 18
  28. 2025Diffuman4D: 4D Consistent Human View Synthesis from Sparse-View Videos with Spatio-Temporal Diffusion Modelscited by 17
  29. 2024Gaussian Splatting in Stylecited by 16
  30. 2024GauU-Scene: A Scene Reconstruction Benchmark on Large Scale 3D Reconstruction Dataset Using Gaussian Splattingcited by 15
  31. 2025PartRM: Modeling Part-Level Dynamics with Large Cross-State Reconstruction Modelcited by 15
  32. 2025MonoSplat: Generalizable 3D Gaussian Splatting from Monocular Depth Foundation Modelscited by 15
  33. 2024A Survey on 3D Human Avatar Modeling -- From Reconstruction to Generationcited by 13
  34. 2025Reconstructing 4D Spatial Intelligence: A Surveycited by 13
  35. 2024Neural Radiance Field-based Visual Rendering: A Comprehensive Reviewcited by 12
  36. 2024Surfel-based Gaussian Inverse Rendering for Fast and Relightable Dynamic Human Reconstruction from Monocular Videocited by 12
  37. 2024SlotLifter: Slot-guided Feature Lifting for Learning Object-centric Radiance Fieldscited by 12
  38. 2025RoGSplat: Learning Robust Generalizable Human Gaussian Splatting from Sparse Multi-View Imagescited by 12

50 most cited of 170 All 170 (JSON)