mlsanityData to 14 Oct 2026

GaussianFlowOcc: Sparse and Weakly Supervised Occupancy Estimation using Gaussian Splatting and Temporal Flow

arXiv 2502.17288 ↗First posted 24 Feb 2025cs.CVcited by 24

Not on the map. Why?

Abstract (arXiv)

Occupancy estimation has become a prominent task in 3D computer vision, particularly within the autonomous driving community. In this paper, we present a novel approach to occupancy estimation, termed GaussianFlowOcc, which is inspired by Gaussian Splatting and replaces traditional dense voxel grids with a sparse 3D Gaussian representation. Our efficient model architecture based on a Gaussian Transformer significantly reduces computational and memory requirements by eliminating the need for expensive 3D convolutions used with inefficient voxel-based representations that predominantly represent empty 3D spaces. GaussianFlowOcc effectively captures scene dynamics by estimating temporal flow for each Gaussian during the overall network training process, offering a straightforward solution to a complex problem that is often neglected by existing methods. Moreover, GaussianFlowOcc is designed for scalability, as it employs weak supervision and does not require costly dense 3D voxel annotations based on additional data (e.g., LiDAR). Through extensive experimentation, we demonstrate that GaussianFlowOcc significantly outperforms all previous methods for weakly supervised occupancy estimation on the nuScenes dataset while featuring an inference speed that is 50 times faster than current SOTA.

Key facts. Cited by 24 papers in the map (data through 14 Oct 2026). Builds on 73 of its 81 references that are in the map. First posted on arXiv 24 Feb 2025.

Builds on

73 of 81 references.

References · 73

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  3. 2023DINOv2: Learning Robust Visual Features without Supervisioncited by 7,974
  4. 2021Emerging Properties in Self-Supervised Vision Transformerscited by 6,968
  5. 20233D Gaussian Splatting for Real-Time Radiance Field Renderingcited by 6,226
  6. 2019nuScenes: A multimodal dataset for autonomous drivingcited by 4,523
  7. 2022Instant Neural Graphics Primitives with a Multiresolution Hash Encodingcited by 3,723
  8. 2021Mip-NeRF 360: Unbounded Anti-Aliased Neural Radiance Fieldscited by 2,032
  9. 2021Mip-NeRF: A Multiscale Representation for Anti-Aliasing Neural Radiance Fieldscited by 1,964
  10. 2020pixelNeRF: Neural Radiance Fields from One or Few Imagescited by 1,584
  11. 2020D-NeRF: Neural Radiance Fields for Dynamic Scenescited by 1,465
  12. 2022BEVFormer: Learning Bird's-Eye-View Representation from Multi-Camera Images via Spatiotemporal Transformerscited by 1,218
38 more
  1. 20234D Gaussian Splatting for Real-Time Dynamic Scene Renderingcited by 1,157
  2. 2024Grounded SAM: Assembling Open-World Models for Diverse Visual Taskscited by 929
  3. 2023K-Planes: Explicit Radiance Fields in Space, Time, and Appearancecited by 746
  4. 2021MVSNeRF: Fast Generalizable Radiance Field Reconstruction from Multi-View Stereocited by 740
  5. 2021BEVDet: High-performance Multi-camera 3D Object Detection in Bird-Eye-Viewcited by 713
  6. 2021Extract Free Dense Labels from CLIPcited by 583
  7. 2024MVSplat: Efficient 3D Gaussian Splatting from Sparse Multi-View Imagescited by 566
  8. 2022PETR: Position Embedding Transformation for Multi-View 3D Object Detectioncited by 552
  9. 2023LERF: Language Embedded Radiance Fieldscited by 543
  10. 2022Point-NeRF: Point-based Neural Radiance Fieldscited by 503
  11. 2023LangSplat: 3D Language Gaussian Splattingcited by 415
  12. 2023Tri-Perspective View for Vision-Based 3D Semantic Occupancy Predictioncited by 409
  13. 2023Metric3D: Towards Zero-shot Metric 3D Prediction from A Single Imagecited by 365
  14. 2023Feature 3DGS: Supercharging 3D Gaussian Splatting to Enable Distilled Feature Fieldscited by 364
  15. 2021MonoScene: Monocular 3D Semantic Scene Completioncited by 363
  16. 2023DrivingGaussian: Composite Gaussian Splatting for Surrounding Dynamic Autonomous Driving Scenescited by 360
  17. 2022BEVDet4D: Exploit Temporal Cues in Multi-camera 3D Object Detectioncited by 341
  18. 2023Occ3D: A Large-Scale 3D Occupancy Prediction Benchmark for Autonomous Drivingcited by 332
  19. 2023Exploring Object-Centric Temporal Modeling for Efficient Multi-View 3D Object Detectioncited by 315
  20. 2023VoxFormer: Sparse Voxel Transformer for Camera-based 3D Semantic Scene Completioncited by 313
  21. 2023OccFormer: Dual-path Transformer for Vision-based 3D Semantic Occupancy Predictioncited by 293
  22. 2023OpenOccupancy: A Large Scale Benchmark for Surrounding Semantic Occupancy Perceptioncited by 221
  23. 2024Street Gaussians: Modeling Dynamic Urban Scenes with Gaussian Splattingcited by 221
  24. 2023Scene as Occupancycited by 209
  25. 2023A Simple Framework for Open-Vocabulary Segmentation and Detectioncited by 198
  26. 2023GPS-Gaussian: Generalizable Pixel-wise 3D Gaussian Splatting for Real-time Human Novel View Synthesiscited by 170
  27. 2021Panoptic nuScenes: A Large-Scale Benchmark for LiDAR Panoptic Segmentation and Trackingcited by 166
  28. 2023FB-OCC: 3D Occupancy Prediction based on Forward-Backward View Transformationcited by 165
  29. 2024GaussianFormer: Scene as Gaussians for Vision-Based 3D Semantic Occupancy Predictioncited by 157
  30. 2023SelfOcc: Self-Supervised Vision-Based 3D Occupancy Predictioncited by 133
  31. 2023RenderOcc: Vision-Centric 3D Occupancy Prediction with 2D Rendering Supervisioncited by 128
  32. 2023FlashOcc: Fast and Memory-Efficient Occupancy Prediction via Channel-to-Height Plugincited by 103
  33. 2023COTR: Compact Occupancy TRansformer for Vision-based 3D Occupancy Predictioncited by 96
  34. 2024SparseOcc: Rethinking Sparse Latent Representation for Vision-Based Semantic Occupancy Predictioncited by 96
  35. 2023Symphonize 3D Semantic Scene Completion with Contextual Instance Queriescited by 90
  36. 2024MVSGaussian: Fast Generalizable Gaussian Splatting Reconstruction from Multi-View Stereocited by 87
  37. 2022SurroundDepth: Entangling Surrounding Views for Self-Supervised Multi-Camera Depth Estimationcited by 76
  38. 2024GaussianWorld: Gaussian World Model for Streaming 3D Occupancy Predictioncited by 67

50 most cited of 73 All 73 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 16; 2026: 8.

24 papers.

Sort:

By area:

  1. 2025GS-Occ3D: Scaling Vision-only Occupancy Reconstruction with Gaussian Splattingcited by 11
  2. 2025Semantic Causality-Aware Vision-Based 3D Occupancy Predictioncited by 8
  3. 2025OneOcc: Semantic Occupancy Prediction for Legged Robots with a Single Panoramic Cameracited by 8
  4. 2025Foundation Models for Autonomous Driving Perception: A Survey Through Core Capabilitiescited by 6
  5. 2025ShelfOcc: Native 3D Supervision beyond LiDAR for Vision-Based Occupancy Estimationcited by 6
  6. 2025SQS: Enhancing Sparse Perception Models via Query-based Splatting in Autonomous Drivingcited by 4
  7. 2025Progressive Gaussian Transformer with Anisotropy-aware Sampling for Open Vocabulary Occupancy Predictioncited by 4
  8. 2025Forging Spatial Intelligence: A Roadmap of Multi-Modal Data Pre-Training for Autonomous Systemscited by 4
  9. 2025ODG: Occupancy Prediction Using Dual Gaussianscited by 3
  10. 2025ShelfGaussian: Shelf-Supervised Open-Vocabulary Gaussian-based 3D Scene Understandingcited by 3
  11. 2025Out-of-Distribution Semantic Occupancy Predictioncited by 2
  12. 2025Easy3D-Labels: Supervising Semantic Occupancy Estimation with 3D Pseudo-Labels for Automotive Perceptioncited by 2
12 more
  1. 2025QueryOcc: Query-based Self-Supervision for 3D Semantic Occupancycited by 2
  2. 2026DLWM: Dual Latent World Models enable Holistic Gaussian-centric Pre-training in Autonomous Drivingcited by 2
  3. 2026FreeOcc: Training-Free Embodied Open-Vocabulary Occupancy Predictioncited by 2
  4. 2025BePo: Dual Representation for 3D Occupancy Predictioncited by 1
  5. 2026VEOcc: Voxel-Centric Online Semantic Occupancy Prediction For Embodied Scene Understandingcited by 1
  6. 2025SuperQuadricOcc: Real-Time Self-Supervised Semantic Occupancy Estimation with Superquadric Volume Renderingcited by 0
  7. 2025HyGE-Occ: Hybrid View-Transformation with 3D Gaussian and Edge Priors for 3D Panoptic Occupancy Predictioncited by 0
  8. 2026FreeOcc: Training-free Panoptic Occupancy Prediction via Foundation Modelscited by 0
  9. 2026GEM: Gaussian Evolution Model for Occupancy Forecasting and Motion Planningcited by 0
  10. 2026Deformable Gaussian Occupancy: Decoupling Rigid and Nonrigid Motion with Factorized Distillationcited by 0
  11. 2026LetOccVote: Learning Weakly Supervised 3D Occupancy through Consensuscited by 0
  12. 2026TriO: Tri-Modal Unsupervised Occupancy World Model for Anything Perceptioncited by 0