mlsanityData to 14 Oct 2026

NeuroGauss4D-PCI: 4D Neural Fields and Gaussian Deformation Fields for Point Cloud Interpolation

arXiv 2405.14241 ↗First posted 23 May 2024cs.CV cs.AIcited by 3

Not on the map. Why?

Abstract (arXiv)

Point Cloud Interpolation confronts challenges from point sparsity, complex spatiotemporal dynamics, and the difficulty of deriving complete 3D point clouds from sparse temporal information. This paper presents NeuroGauss4D-PCI, which excels at modeling complex non-rigid deformations across varied dynamic scenes. The method begins with an iterative Gaussian cloud soft clustering module, offering structured temporal point cloud representations. The proposed temporal radial basis function Gaussian residual utilizes Gaussian parameter interpolation over time, enabling smooth parameter transitions and capturing temporal residuals of Gaussian distributions. Additionally, a 4D Gaussian deformation field tracks the evolution of these parameters, creating continuous spatiotemporal deformation fields. A 4D neural field transforms low-dimensional spatiotemporal coordinates (x,y,z,t) into a high-dimensional latent space. Finally, we adaptively and efficiently fuse the latent features from neural fields and the geometric features from Gaussian deformation fields. NeuroGauss4D-PCI outperforms existing methods in point cloud frame interpolation, delivering leading performance on both object-level (DHB) and large-scale autonomous driving datasets (NL-Drive), with scalability to auto-labeling and point cloud densification tasks. The source code is released at https://github.com/jiangchaokang/NeuroGauss4D-PCI.

Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Builds on 45 of its 58 references that are in the map. First posted on arXiv 23 May 2024.

Builds on

45 of 58 references.

References · 45

  1. 20233D Gaussian Splatting for Real-Time Radiance Field Renderingcited by 6,226
  2. 2019nuScenes: A multimodal dataset for autonomous drivingcited by 4,523
  3. 2018Dynamic Graph CNN for Learning on Point Cloudscited by 2,223
  4. 2021Alias-Free Generative Adversarial Networkscited by 1,184
  5. 20234D Gaussian Splatting for Real-Time Dynamic Scene Renderingcited by 1,157
  6. 2019Argoverse: 3D Tracking and Forecasting with Rich Mapscited by 732
  7. 2018Open3D: A Modern Library for 3D Data Processingcited by 721
  8. 2018FlowNet3D: Learning Scene Flow in 3D Point Cloudscited by 242
  9. 2024A Survey on 3D Gaussian Splattingcited by 224
  10. 2021NEAT: Neural Attention Fields for End-to-End Autonomous Drivingcited by 174
  11. 20183D-CODED : 3D Correspondences by Deep Deformationcited by 160
  12. 2021Offboard 3D Object Detection from Point Cloud Sequencescited by 145
33 more
  1. 2019HPLFlowNet: Hierarchical Permutohedral Lattice FlowNet for Scene Flow Estimation on Large-scale Point Cloudscited by 109
  2. 2020S3CNet: A Sparse Semantic Scene Completion Network for LiDAR Point Cloudscited by 102
  3. 2024STAG4D: Spatial-Temporal Anchored Generative 4D Gaussianscited by 102
  4. 2024GaussianFlow: Splatting Gaussian Dynamics for 4D Content Creationcited by 100
  5. 2021Neural Scene Flow Priorcited by 91
  6. 2023Implicit Neural Representation in Medical Imaging: A Comparative Surveycited by 90
  7. 2023UltraLiDAR: Learning Compact Representations for LiDAR Completion and Generationcited by 78
  8. 2020PV-RAFT: Point-Voxel Correlation Fields for Scene Flow Estimation of Point Cloudscited by 74
  9. 2024Deblurring 3D Gaussian Splattingcited by 66
  10. 2023SNI-SLAM: Semantic Neural Implicit SLAMcited by 65
  11. 2024SemGauss-SLAM: Dense Semantic Gaussian Splatting SLAMcited by 42
  12. 2023Fast Neural Scene Flowcited by 41
  13. 2022HSC4D: Human-centered 4D Scene Capture in Large-scale Indoor-outdoor Space Using Wearable IMUs and LiDARcited by 38
  14. 2022Bi-PointFlowNet: Bidirectional Learning for Point Cloud Based Scene Flow Estimationcited by 38
  15. 2023RegFormer: An Efficient Projection-Aware Transformer Network for Large-Scale Point Cloud Registrationcited by 37
  16. 2022Generalised Implicit Neural Representationscited by 31
  17. 2022SCOOP: Self-Supervised Correspondence and Optimization-Based Scene Flowcited by 28
  18. 2024DVLO: Deep Visual-LiDAR Odometry with Local-to-Global Feature Fusion and Bi-Directional Structure Alignmentcited by 26
  19. 2023Self-Supervised 3D Scene Flow Estimation Guided by Superpointscited by 24
  20. 2023Local Implicit Ray Function for Generalizable Radiance Field Representationcited by 19
  21. 2022Neural Implicit Surface Evolutioncited by 18
  22. 2023Neural Vector Fields: Implicit Representation by Explicit Learningcited by 16
  23. 20243DSFLabelling: Boosting 3D Scene Flow Estimation by Pseudo Auto-labellingcited by 16
  24. 2020MoNet: Motion-based Point Cloud Prediction Networkcited by 14
  25. 2023GMSF: Global Matching Scene Flowcited by 14
  26. 2023NeuralPCI: Spatio-temporal Neural Field for 3D Point Cloud Multi-frame Non-linear Interpolationcited by 13
  27. 2020PointINet: Point Cloud Frame Interpolation Networkcited by 12
  28. 2023DifFlow3D: Toward Robust Uncertainty-Aware Scene Flow Estimation with Diffusion Modelcited by 11
  29. 2022IDEA-Net: Dynamic 3D Point Cloud Interpolation via Deep Embedding Alignmentcited by 9
  30. 20223D Scene Flow Estimation on Pseudo-LiDAR: Bridging the Gap on Estimating Point Motioncited by 7
  31. 2022FFPA-Net: Efficient Feature Fusion with Projection Awareness for 3D Object Detectioncited by 3
  32. 2022Pseudo-LiDAR for Visual Odometrycited by 2
  33. 2022Unsupervised Learning of 3D Scene Flow with 3D Odometry Assistancecited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 1; 2026: 2.

3 papers.

  1. 20254DSTR: Advancing Generative 4D Gaussians with Spatial-Temporal Rectification for High-Quality and Consistent 4D Generationcited by 5
  2. 2026RegFormer++: An Efficient Large-Scale 3D LiDAR Point Registration Network with Projection-Aware 2D Transformercited by 3
  3. 2026RoGS: Adaptive Meshgrid Gaussian for Large-Scale Road Surface Mappingcited by 0