mlsanityData to 14 Oct 2026

Compressing Explicit Voxel Grid Representations: fast NeRFs become also small

arXiv 2210.12782 ↗First posted 23 Oct 2022cs.CV cs.AIcited by 48

Not on the map. Why?

Abstract (arXiv)

NeRFs have revolutionized the world of per-scene radiance field reconstruction because of their intrinsic compactness. One of the main limitations of NeRFs is their slow rendering speed, both at training and inference time. Recent research focuses on the optimization of an explicit voxel grid (EVG) that represents the scene, which can be paired with neural networks to learn radiance fields. This approach significantly enhances the speed both at train and inference time, but at the cost of large memory occupation. In this work we propose Re:NeRF, an approach that specifically targets EVG-NeRFs compressibility, aiming to reduce memory storage of NeRF models while maintaining comparable performance. We benchmark our approach with three different EVG-NeRF architectures on four popular benchmarks, showing Re:NeRF's broad usability and effectiveness.

Key facts. Cited by 48 papers in the map (data through 14 Oct 2026). Builds on 35 of its 47 references that are in the map. First posted on arXiv 23 Oct 2022.

Builds on

35 of 47 references.

References · 35

  1. 2022Instant Neural Graphics Primitives with a Multiresolution Hash Encodingcited by 3,723
  2. 2018The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networkscited by 2,262
  3. 2015Learning both Weights and Connections for Efficient Neural Networkscited by 2,031
  4. 2021Plenoxels: Radiance Fields without Neural Networkscited by 1,613
  5. 2020pixelNeRF: Neural Radiance Fields from One or Few Imagescited by 1,584
  6. 2022TensoRF: Tensorial Radiance Fieldscited by 1,280
  7. 2020NeRF in the Wild: Neural Radiance Fields for Unconstrained Photo Collectionscited by 1,232
  8. 2021Direct Voxel Grid Optimization: Super-fast Convergence for Radiance Fields Reconstructioncited by 964
  9. 2020Neural Sparse Voxel Fieldscited by 959
  10. 2018SNIP: Single-shot Network Pruning based on Connection Sensitivitycited by 812
  11. 2020Neural Scene Flow Fields for Space-Time View Synthesis of Dynamic Scenescited by 751
  12. 2020pi-GAN: Periodic Implicit Generative Adversarial Networks for 3D-Aware Image Synthesiscited by 708
23 more
  1. 2020GRAF: Generative Radiance Fields for 3D-Aware Image Synthesiscited by 689
  2. 2021KiloNeRF: Speeding up Neural Radiance Fields with Thousands of Tiny MLPscited by 673
  3. 2019Local Light Field Fusion: Practical View Synthesis with Prescriptive Sampling Guidelinescited by 672
  4. 2020NeRV: Neural Reflectance and Visibility Fields for Relighting and View Synthesiscited by 496
  5. 2020Non-Rigid Neural Radiance Fields: Reconstruction and Novel View Synthesis of a Dynamic Scene From Monocular Videocited by 471
  6. 2020Dynamic Neural Radiance Fields for Monocular 4D Facial Avatar Reconstructioncited by 467
  7. 2020NeRD: Neural Reflectance Decomposition from Image Collectionscited by 449
  8. 2021Dynamic View Synthesis from Dynamic Monocular Videocited by 420
  9. 2020Space-time Neural Irradiance Fields for Free-Viewpoint Videocited by 414
  10. 2019Deferred Neural Rendering: Image Synthesis using Neural Texturescited by 253
  11. 2019DeepView: View Synthesis with Learned Gradient Descentcited by 253
  12. 2020Learned Initializations for Optimizing Coordinate-Based Neural Representationscited by 242
  13. 2021Neural Articulated Radiance Fieldcited by 196
  14. 2019Pushing the Boundaries of View Extrapolation with Multiplane Imagescited by 191
  15. 2022StylizedNeRF: Consistent 3D Scene Stylization as Stylized NeRF via 2D-3D Mutual Learningcited by 140
  16. 2021NeRF-VAE: A Geometry Aware 3D Scene Generative Modelcited by 112
  17. 2020Crowdsampling the Plenoptic Functioncited by 62
  18. 2021Fast and Explicit Neural View Synthesiscited by 28
  19. 2018Learning Sparse Neural Networks via Sensitivity-Driven Regularizationcited by 26
  20. 2021Neural Radiance Fields Approach to Deep Multi-View Photometric Stereocited by 25
  21. 2020LOss-Based SensiTivity rEgulaRization: towards deep sparse neural networkscited by 19
  22. 2021SeReNe: Sensitivity based Regularization of Neurons for Structured Sparsity in Neural Networkscited by 12
  23. 2022Distilled Low Rank Neural Radiance Field with Quantization for Light Field Compressioncited by 5

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 2; 2023: 15; 2024: 19; 2025: 9; 2026: 3.

48 papers.

Sort:

  1. 2023Compressed 3D Gaussian Splatting for Accelerated Novel View Synthesiscited by 239
  2. 2023MERF: Memory-Efficient Radiance Fields for Real-time View Synthesis in Unbounded Scenescited by 218
  3. 2024Mini-Splatting: Representing Scenes with a Constrained Number of Gaussianscited by 213
  4. 2024HAC: Hash-grid Assisted Context for 3D Gaussian Splatting Compressioncited by 209
  5. 2023Compact 3D Scene Representation via Self-Organizing Gaussian Gridscited by 151
  6. 2023CompGS: Smaller and Faster Gaussian Splatting with Vector Quantizationcited by 130
  7. 2024End-to-End Rate-Distortion Optimized 3D Gaussian Representationcited by 75
  8. 2022Compressing Volumetric Radiance Fields to 1 MBcited by 68
  9. 2022Masked Wavelet Representation for Compact Neural Radiance Fieldscited by 57
  10. 2025HAC++: Towards 100X Compression of 3D Gaussian Splattingcited by 57
  11. 2024MesonGS: Post-training Compression of 3D Gaussians via Efficient Attribute Transformationcited by 56
  12. 2024Fast Feedforward 3D Gaussian Splatting Compressioncited by 52
36 more
  1. 2024Trimming the Fat: Efficient Compression of 3D Gaussian Splats through Pruningcited by 47
  2. 2023Binary Radiance Fieldscited by 40
  3. 2024How Far Can We Compress Instant-NGP-Based NeRF?cited by 30
  4. 2023NeRFLiX: High-Quality Neural View Synthesis by Learning a Degradation-Driven Inter-viewpoint MiXercited by 29
  5. 20254DGC: Rate-Aware 4D Gaussian Compression for Efficient Streamable Free-Viewpoint Videocited by 27
  6. 2023VideoRF: Rendering Dynamic Radiance Fields as 2D Feature Video Streamscited by 22
  7. 2023TeTriRF: Temporal Tri-Plane Radiance Fields for Efficient Free-Viewpoint Videocited by 22
  8. 2024Implicit Gaussian Splatting with Efficient Multi-Level Tri-Plane Representationcited by 21
  9. 2024ELMGS: Enhancing memory and computation scaLability through coMpression for 3D Gaussian Splattingcited by 20
  10. 2024NeRFCodec: Neural Feature Compression Meets Neural Radiance Fields for Memory-Efficient Scene Representationcited by 16
  11. 2023SlimmeRF: Slimmable Radiance Fieldscited by 15
  12. 2024Efficient Scene Modeling via Structure-Aware and Region-Prioritized 3D Gaussianscited by 15
  13. 2024HPC: Hierarchical Progressive Coding Framework for Volumetric Videocited by 13
  14. 20246DOPE-GS: Online 6D Object Pose Estimation using Gaussian Splattingcited by 11
  15. 2025GoDe: Gaussians on Demand for Progressive Level of Detail and Scalable Compressioncited by 11
  16. 2023Targeted Adversarial Attacks on Generalizable Neural Radiance Fieldscited by 10
  17. 2023ECRF: Entropy-Constrained Neural Radiance Fields Compression with Frequency Domain Optimizationcited by 8
  18. 2024Explicit-NeRF-QA: A Quality Assessment Database for Explicit NeRF Model Compressioncited by 8
  19. 2023From NeRFLiX to NeRFLiX++: A General NeRF-Agnostic Restorer Paradigmcited by 7
  20. 2024Content-Aware Radiance Fields: Aligning Model Complexity with Scene Intricacy Through Learned Bitwidth Quantizationcited by 7
  21. 2024CodecNeRF: Toward Fast Encoding and Decoding, Compact, and High-quality Novel-view Synthesiscited by 6
  22. 2023CAwa-NeRF: Instant Learning of Compression-Aware NeRF Featurescited by 4
  23. 2024SPC-NeRF: Spatial Predictive Compression for Voxel Based Radiance Fieldcited by 4
  24. 2024Neural NeRF Compressioncited by 4
  25. 2025Optimized 3D Gaussian Splatting using Coarse-to-Fine Image Frequency Modulationcited by 4
  26. 2025FlexGS: Train Once, Deploy Everywhere with Many-in-One Flexible 3D Gaussian Splattingcited by 3
  27. 2026POTR: Post-Training 3DGS Compressioncited by 3
  28. 2024NGP-RT: Fusing Multi-Level Hash Features with Lightweight Attention for Real-Time Novel View Synthesiscited by 2
  29. 2025Exploring Kernel Transformations for Implicit Neural Representationscited by 2
  30. 2025Efficient Neural Video Representation with Temporally Coherent Modulationcited by 2
  31. 2023Semantic-Human: Neural Rendering of Humans from Monocular Video with Human Parsingcited by 1
  32. 2025NeRFlex: Resource-aware Real-time High-quality Rendering of Complex Scenes on Mobile Devicescited by 1
  33. 2025TimeNeRF: Building Generalizable Neural Radiance Fields across Time from Few-Shot Input Viewscited by 1
  34. 2026Factorized Multi-Resolution HashGrid for Efficient Neural Radiance Fields: Execution on Edge-Devicescited by 1
  35. 2023Learn how to Prune Pixels for Multi-view Neural Image-based Synthesiscited by 0
  36. 2026MesonGS++: Post-training Compression of 3D Gaussian Splatting with Hyperparameter Searchingcited by 0