mlsanityData to 7 Oct 2026

Recent Advances and Trends in Learning-based 3D Representations

arXiv 2606.04871 ↗First posted 3 Jun 2026cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

The selection of an appropriate 3D representation is a fundamental design decision that dictates the efficiency, quality, and capabilities of modern computer vision and graphics pipelines for tasks such as 3D reconstruction, novel-view synthesis and rendering, shape and motion analysis, recognition, and generation. While traditional representations (eg meshes, point clouds, and volumetric grids) remain standard outputs of 3D sensors (eg LiDAR and 3D scanners) and are widely used in downstream applications (eg editing and simulation), recent neural and primitive-based representations (eg 3D Gaussian Splatting) offer compact and differentiable alternatives opening a wide range of opportunities in applications such as games, AR/VR, autonomous driving, robot navigation, and medical imaging, to name a few. The goal of this paper is to survey the main families of 3D representations from discrete explicit formats to continuous implicit fields based either on neural rendering or primitive splatting. For each type of representation, we present the general formulation and its variants, discuss its benefits and limitations, and highlight key applications. We conclude the paper by outlining the open challenges and potential directions for future research. Distinct from recent surveys that broadly cover 3D object and scene reconstruction, this paper provides a focused analysis on the evolution of 3D representations themselves. We specifically emphasize the paradigm shift toward implicit representations, offering a novel perspective on how these emerging formats fundamentally alter 3D/4D workflows.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 88 of its 111 references that are in the map. First posted on arXiv 3 Jun 2026.

Builds on

88 of 111 references.

References · 88

  1. 2017Attention Is All You Needcited by 59,932
  2. 20233D Gaussian Splatting for Real-Time Radiance Field Renderingcited by 6,141
  3. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,384
  4. 2022Instant Neural Graphics Primitives with a Multiresolution Hash Encodingcited by 3,698
  5. 2018Dynamic Graph CNN for Learning on Point Cloudscited by 2,220
  6. 2020Implicit Neural Representations with Periodic Activation Functionscited by 2,214
  7. 2020Fourier Features Let Networks Learn High Frequency Functions in Low Dimensional Domainscited by 2,170
  8. 2021NeuS: Learning Neural Implicit Surfaces by Volume Rendering for Multi-view Reconstructioncited by 1,701
  9. 20242D Gaussian Splatting for Geometrically Accurate Radiance Fieldscited by 1,061
  10. 2020Neural Sparse Voxel Fieldscited by 959
  11. 2019Scene Representation Networks: Continuous 3D-Structure-Aware Neural Scene Representationscited by 864
  12. 2020NeRF++: Analyzing and Improving Neural Radiance Fieldscited by 857
38 more
  1. 2018PointCNN: Convolution On X-Transformed Pointscited by 764
  2. 2023K-Planes: Explicit Radiance Fields in Space, Time, and Appearancecited by 742
  3. 2019Local Light Field Fusion: Practical View Synthesis with Prescriptive Sampling Guidelinescited by 672
  4. 2023Zip-NeRF: Anti-Aliased Grid-Based Neural Radiance Fieldscited by 667
  5. 2023Mip-Splatting: Alias-free 3D Gaussian Splattingcited by 661
  6. 2023One-2-3-45: Any Single Image to 3D Mesh in 45 Seconds without Per-Shape Optimizationcited by 555
  7. 2021Neural Fields in Visual Computing and Beyondcited by 539
  8. 2022Point Transformer V2: Grouped Vector Attention and Partition-based Poolingcited by 384
  9. 2023PhysGaussian: Physics-Integrated 3D Gaussians for Generative Dynamicscited by 368
  10. 2022Fast Dynamic Radiance Fields with Time-Aware Neural Voxelscited by 344
  11. 2022MobileNeRF: Exploiting the Polygon Rasterization Pipeline for Efficient Neural Field Rendering on Mobile Architecturescited by 308
  12. 2021Mixture of Volumetric Primitives for Efficient Neural Renderingcited by 277
  13. 2024DNGaussian: Optimizing Sparse-View 3D Gaussian Radiance Fields with Global-Local Depth Normalizationcited by 256
  14. 2021NeuralRecon: Real-Time Coherent 3D Reconstruction from Monocular Videocited by 241
  15. 2024No Pose, No Problem: Surprisingly Simple 3D Gaussian Splats from Sparse Unposed Imagescited by 241
  16. 2022NoPe-NeRF: Optimising Neural Radiance Field with No Pose Priorcited by 235
  17. 2021DONeRF: Towards Real-Time Rendering of Compact Neural Radiance Fields using Depth Oracle Networkscited by 232
  18. 2024Gaussian Opacity Fields: Efficient Adaptive Surface Reconstruction in Unbounded Scenescited by 226
  19. 2024A Hierarchical 3D Gaussian Representation for Real-Time Rendering of Very Large Datasetscited by 214
  20. 2021HyperNeRF: A Higher-Dimensional Representation for Topologically Varying Neural Radiance Fieldscited by 210
  21. 2023Robust Dynamic Radiance Fieldscited by 193
  22. 2022Embodied Hands: Modeling and Capturing Hands and Bodies Togethercited by 179
  23. 2019Neural Volumes: Learning Dynamic Renderable Volumes from Imagescited by 173
  24. 2024PointMamba: A Simple State Space Model for Point Cloud Analysiscited by 166
  25. 2020DiffusionNet: Discretization Agnostic Learning on Surfacescited by 163
  26. 2023NeRO: Neural Geometry and BRDF Reconstruction of Reflective Objects from Multiview Imagescited by 163
  27. 2021Efficient Neural Radiance Fields for Interactive Free-viewpoint Videocited by 150
  28. 2023Compact 3D Scene Representation via Self-Organizing Gaussian Gridscited by 147
  29. 20243D Gaussian Ray Tracing: Fast Tracing of Particle Scenescited by 138
  30. 2021NeRS: Neural Reflectance Surfaces for Sparse-view 3D Reconstruction in the Wildcited by 136
  31. 2024Reducing the Memory Footprint of 3D Gaussian Splattingcited by 129
  32. 2023DynMF: Neural Motion Factorization for Real-time Dynamic View Synthesis with 3D Gaussian Splattingcited by 124
  33. 2022Variable Bitrate Neural Fieldscited by 116
  34. 2024StopThePop: Sorted Gaussian Splatting for View-Consistent Real-time Renderingcited by 107
  35. 2021Neural Actor: Neural Free-view Synthesis of Human Actors with Pose Controlcited by 106
  36. 2023OctFormer: Octree-based Transformers for 3D Point Cloudscited by 105
  37. 2023Grid-guided Neural Radiance Fields for Large Urban Scenescited by 99
  38. 2018MeshNet: Mesh Neural Network for 3D Shape Representationcited by 95

50 most cited of 88 All 88 (JSON)

Built on by

Not cited yet.