mlsanityData to 7 Oct 2026

Neural Rendering and Its Hardware Acceleration: A Review

arXiv 2402.00028 ↗First posted 6 Jan 2024cs.GR cs.CV eess.IVcited by 4

Not on the map. Why?

Abstract (arXiv)

Neural rendering is a new image and video generation method based on deep learning. It combines the deep learning model with the physical knowledge of computer graphics, to obtain a controllable and realistic scene model, and realize the control of scene attributes such as lighting, camera parameters, posture and so on. On the one hand, neural rendering can not only make full use of the advantages of deep learning to accelerate the traditional forward rendering process, but also provide new solutions for specific tasks such as inverse rendering and 3D reconstruction. On the other hand, the design of innovative hardware structures that adapt to the neural rendering pipeline breaks through the parallel computing and power consumption bottleneck of existing graphics processors, which is expected to provide important support for future key areas such as virtual and augmented reality, film and television creation and digital entertainment, artificial intelligence and the metaverse. In this paper, we review the technical connotation, main challenges, and research progress of neural rendering. On this basis, we analyze the common requirements of neural rendering pipeline for hardware acceleration and the characteristics of the current hardware acceleration architecture, and then discuss the design challenges of neural rendering processor architecture. Finally, the future development trend of neural rendering processor architecture is prospected.

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Builds on 66 of its 128 references that are in the map. First posted on arXiv 6 Jan 2024.

Builds on

66 of 128 references.

References · 66

  1. 2022Instant Neural Graphics Primitives with a Multiresolution Hash Encodingcited by 3,698
  2. 2019DeepSDF: Learning Continuous Signed Distance Functions for Shape Representationcited by 2,682
  3. 2020pixelNeRF: Neural Radiance Fields from One or Few Imagescited by 1,574
  4. 2020D-NeRF: Neural Radiance Fields for Dynamic Scenescited by 1,459
  5. 2018Learning Implicit Fields for Generative Shape Modelingcited by 1,060
  6. 2021Volume Rendering of Neural Implicit Surfacescited by 990
  7. 2020Neural Sparse Voxel Fieldscited by 959
  8. 2021PlenOctrees for Real-time Rendering of Neural Radiance Fieldscited by 904
  9. 2019Scene Representation Networks: Continuous 3D-Structure-Aware Neural Scene Representationscited by 864
  10. 2020GIRAFFE: Representing Scenes as Compositional Generative Neural Feature Fieldscited by 784
  11. 2020Neural Scene Flow Fields for Space-Time View Synthesis of Dynamic Scenescited by 750
  12. 2022Block-NeRF: Scalable Large Scene Neural View Synthesiscited by 720
38 more
  1. 2019Differentiable Volumetric Rendering: Learning Implicit 3D Representations without 3D Supervisioncited by 699
  2. 2021IBRNet: Learning Multi-View Image-Based Renderingcited by 698
  3. 2021KiloNeRF: Speeding up Neural Radiance Fields with Thousands of Tiny MLPscited by 672
  4. 2021Common Objects in 3D: Large-Scale Learning and Evaluation of Real-life 3D Category Reconstructioncited by 646
  5. 2021FastNeRF: High-Fidelity Neural Rendering at 200FPScited by 510
  6. 2018DeepVoxels: Learning Persistent 3D Feature Embeddingscited by 401
  7. 2021Advances in Neural Renderingcited by 365
  8. 2019SynSin: End-to-end View Synthesis from a Single Imagecited by 364
  9. 2021Light Field Networks: Neural Scene Representations with Single-Evaluation Renderingcited by 330
  10. 2019Neural Point-Based Graphicscited by 326
  11. 2022MobileNeRF: Exploiting the Polygon Rasterization Pipeline for Efficient Neural Field Rendering on Mobile Architecturescited by 308
  12. 2020State of the Art on Neural Renderingcited by 276
  13. 2019Texture Fields: Learning Texture Representations in Function Spacecited by 210
  14. 2020AutoInt: Automatic Integration for Fast Neural Volume Renderingcited by 204
  15. 2023TPU v4: An Optically Reconfigurable Supercomputer for Machine Learning with Hardware Support for Embeddingscited by 198
  16. 2021GeoNeRF: Generalizing NeRF with Geometry Priorscited by 195
  17. 2021Point-Based Neural Rendering with Per-View Optimizationcited by 188
  18. 2023Extracting Motion and Appearance via Inter-Frame Attention for Efficient Video Frame Interpolationcited by 97
  19. 2022Learning-based Inverse Rendering of Complex Indoor Scenes with Differentiable Monte Carlo Raytracingcited by 78
  20. 2020Neural Light Transport for Relighting and View Synthesiscited by 73
  21. 2022DP-NeRF: Deblurred Neural Radiance Field with Physical Scene Priorscited by 70
  22. 2022R2L: Distilling Neural Radiance Field to Neural Light Field for Efficient Novel View Synthesiscited by 69
  23. 2019Neural Point Cloud Rendering via Multi-Plane Projectioncited by 60
  24. 2023Instant-3D: Instant Neural Radiance Field Training Towards On-Device AR/VR 3D Reconstructioncited by 49
  25. 2022Real-Time Neural Light Field on Mobile Devicescited by 48
  26. 2016Deep Shading: Convolutional Neural Networks for Screen-Space Shadingcited by 46
  27. 2018RenderNet: A deep convolutional network for differentiable rendering from 3D shapescited by 42
  28. 2023I2-SDF: Intrinsic Indoor Scene Reconstruction and Editing via Raytracing in Neural SDFscited by 42
  29. 2021NeLF: Neural Light-transport Field for Portrait View Synthesis and Relightingcited by 38
  30. 2020Neural Control Variatescited by 34
  31. 2021Neural Radiositycited by 33
  32. 2022ImmFusion: Robust mmWave-RGB Fusion for 3D Human Body Reconstruction in All Weather Conditionscited by 21
  33. 2022Contact2Grasp: 3D Grasp Synthesis via Hand-Object Contact Constraintcited by 21
  34. 2019Neural Voxel Renderer: Learning an Accurate and Controllable Rendering Toolcited by 20
  35. 2023Seal-3D: Interactive Pixel-Level Editing for Neural Radiance Fieldscited by 18
  36. 2020Deep CG2Real: Synthetic-to-Real Translation via Image Disentanglementcited by 15
  37. 2023Hardware Acceleration of Neural Graphicscited by 10
  38. 2017Deep Illumination: Approximating Dynamic Global Illumination with Generative Adversarial Networkcited by 7

50 most cited of 66 All 66 (JSON)

Built on by

Cited by year

Citing papers per year: 2024: 2; 2025: 2.

4 papers.

  1. 2024AI-Driven Innovations in Volumetric Video Streaming: A Reviewcited by 2
  2. 2025DNRSelect: Active Best View Selection for Deferred Neural Renderingcited by 2
  3. 2025GaussianHeadTalk: Wobble-Free 3D Talking Heads with Audio Driven Gaussian Splattingcited by 2
  4. 2024Editing Implicit and Explicit Representations of Radiance Fields: A Surveycited by 1