mlsanityData to 14 Oct 2026

TermiNeRF: Ray Termination Prediction for Efficient Neural Rendering

arXiv 2111.03643 ↗First posted 5 Nov 2021cs.CV cs.GRcited by 70

Not on the map. Why?

Abstract (arXiv)

Volume rendering using neural fields has shown great promise in capturing and synthesizing novel views of 3D scenes. However, this type of approach requires querying the volume network at multiple points along each viewing ray in order to render an image, resulting in very slow rendering times. In this paper, we present a method that overcomes this limitation by learning a direct mapping from camera rays to locations along the ray that are most likely to influence the pixel's final appearance. Using this approach we are able to render, train and fine-tune a volumetrically-rendered neural field model an order of magnitude faster than standard approaches. Unlike existing methods, our approach works with general volumes and can be trained end-to-end.

Key facts. Cited by 70 papers in the map (data through 14 Oct 2026). Builds on 18 of its 22 references that are in the map. First posted on arXiv 5 Nov 2021.

Builds on

18 of 22 references.

References · 18

  1. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,177
  2. 2019DeepSDF: Learning Continuous Signed Distance Functions for Shape Representationcited by 2,689
  3. 2018Occupancy Networks: Learning 3D Reconstruction in Function Spacecited by 2,041
  4. 2020pixelNeRF: Neural Radiance Fields from One or Few Imagescited by 1,584
  5. 2021MLP-Mixer: An all-MLP Architecture for Visioncited by 1,446
  6. 2020NeRF in the Wild: Neural Radiance Fields for Unconstrained Photo Collectionscited by 1,232
  7. 2018Learning Implicit Fields for Generative Shape Modelingcited by 1,060
  8. 2021PlenOctrees for Real-time Rendering of Neural Radiance Fieldscited by 905
  9. 2021MVSNeRF: Fast Generalizable Radiance Field Reconstruction from Multi-View Stereocited by 740
  10. 2021Depth-supervised NeRF: Fewer Views and Faster Training for Freecited by 735
  11. 2019Differentiable Volumetric Rendering: Learning Implicit 3D Representations without 3D Supervisioncited by 700
  12. 2021KiloNeRF: Speeding up Neural Radiance Fields with Thousands of Tiny MLPscited by 673
6 more
  1. 2021FastNeRF: High-Fidelity Neural Rendering at 200FPScited by 511
  2. 2021DONeRF: Towards Real-Time Rendering of Compact Neural Radiance Fields using Depth Oracle Networkscited by 232
  3. 2020AutoInt: Automatic Integration for Fast Neural Volume Renderingcited by 204
  4. 2020DeRF: Decomposed Radiance Fieldscited by 163
  5. 2021How to represent part-whole hierarchies in a neural networkcited by 123
  6. 2021NeRF in detail: Learning to sample for view synthesiscited by 35

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 7; 2022: 18; 2023: 23; 2024: 13; 2025: 7; 2026: 2.

70 papers.

Sort:

  1. 2021Mip-NeRF 360: Unbounded Anti-Aliased Neural Radiance Fieldscited by 2,032
  2. 2021Plenoxels: Radiance Fields without Neural Networkscited by 1,613
  3. 2021Advances in Neural Renderingcited by 365
  4. 2022Fast Dynamic Radiance Fields with Time-Aware Neural Voxelscited by 346
  5. 2023Spacetime Gaussian Feature Splatting for Real-Time Dynamic View Synthesiscited by 344
  6. 2023MERF: Memory-Efficient Radiance Fields for Real-time View Synthesis in Unbounded Scenescited by 218
  7. 2023Gaussian-Flow: 4D Reconstruction with Dynamic 3D Gaussian Particlecited by 211
  8. 2022From data to functa: Your data point is a function and you can treat it like onecited by 187
  9. 2023HyperReel: High-Fidelity 6-DoF Video with Ray-Conditioned Samplingcited by 174
  10. 2022NeRFPlayer: A Streamable Dynamic Scene Representation with Decomposed Neural Radiance Fieldscited by 152
  11. 2021Efficient Neural Radiance Fields for Interactive Free-viewpoint Videocited by 150
  12. 2024Per-Gaussian Embedding-Based Deformation for Deformable 3D Gaussian Splattingcited by 104
38 more
  1. 2022BAD-NeRF: Bundle Adjusted Deblur Neural Radiance Fieldscited by 80
  2. 2022R2L: Distilling Neural Radiance Field to Neural Light Field for Efficient Novel View Synthesiscited by 69
  3. 2022AdaNeRF: Adaptive Sampling for Real-time Rendering of Neural Radiance Fieldscited by 68
  4. 2023Forward Flow for Novel View Synthesis of Dynamic Scenescited by 68
  5. 2024BAD-Gaussians: Bundle Adjusted Deblur Gaussian Splattingcited by 61
  6. 2023Urban Radiance Field Representation with Deformable Neural Mesh Primitivescited by 55
  7. 2021Recovery of Continuous 3D Refractive Index Maps from Discrete Intensity-Only Measurements using Neural Fieldscited by 48
  8. 2022Neural Deformable Voxel Grid for Fast Optimization of Dynamic View Synthesiscited by 43
  9. 2022StegaNeRF: Embedding Invisible Information within Neural Radiance Fieldscited by 32
  10. 2023HybridNeRF: Efficient Neural Rendering via Adaptive Volumetric Surfacescited by 28
  11. 2022NeurMiPs: Neural Mixture of Planar Experts for View Synthesiscited by 23
  12. 2021NeuSample: Neural Sample Field for Efficient View Synthesiscited by 21
  13. 2022360Roam: Real-Time Indoor Roaming Using Geometry-Aware 360^circ Radiance Fieldscited by 20
  14. 20223D-Aware Video Generationcited by 17
  15. 2024NeRFs in Robotics: A Surveycited by 16
  16. 2024Improving Physics-Augmented Continuum Neural Radiance Field-Based Geometry-Agnostic System Identification with Lagrangian Particle Optimizationcited by 16
  17. 2022SteerNeRF: Accelerating NeRF Rendering via Smooth Viewpoint Trajectorycited by 15
  18. 2021VaxNeRF: Revisiting the Classic for Voxel-Accelerated Neural Radiance Fieldcited by 14
  19. 2023City-on-Web: Real-time Neural Rendering of Large-scale Scenes on the Webcited by 14
  20. 2022CLONeR: Camera-Lidar Fusion for Occupancy Grid-aided Neural Representationscited by 13
  21. 2024What You See is What You GAN: Rendering Every Pixel for High-Fidelity Geometry in 3D GANscited by 12
  22. 2024Lightning NeRF: Efficient Hybrid Scene Representation for Autonomous Drivingcited by 12
  23. 2023USB-NeRF: Unrolling Shutter Bundle Adjusted Neural Radiance Fieldscited by 11
  24. 2025The NeRF Signature: Codebook-Aided Watermarking for Neural Radiance Fieldscited by 10
  25. 2022FIRe: Fast Inverse Rendering using Directional and Signed Distance Functionscited by 9
  26. 2023Compact Real-time Radiance Fields with Neural Codebookcited by 9
  27. 2023MoBluRF: Motion Deblurring Neural Radiance Fields for Blurry Monocular Videocited by 9
  28. 2024Semantically-aware Neural Radiance Fields for Visual Scene Understanding: A Comprehensive Reviewcited by 9
  29. 2022Progressively-connected Light Field Network for Efficient View Synthesiscited by 8
  30. 2023BAA-NGP: Bundle-Adjusting Accelerated Neural Graphics Primitivescited by 8
  31. 2023Efficient Ray Sampling for Radiance Fields Reconstructioncited by 8
  32. 2023MIMO-NeRF: Fast Neural Rendering with Multi-input Multi-output Neural Radiance Fieldscited by 7
  33. 2024SMURF: Continuous Dynamics for Motion-Deblurring Radiance Fieldscited by 6
  34. 2023Reconstructive Latent-Space Neural Radiance Fields for Efficient 3D Scene Representationscited by 5
  35. 2022Fast Non-Rigid Radiance Fields from Monocularized Datacited by 4
  36. 2023L0-Sampler: An L0 Model Guided Volume Sampling for NeRFcited by 4
  37. 2024CombiNeRF: A Combination of Regularization Techniques for Few-Shot Neural Radiance Field View Synthesiscited by 4
  38. 2024HashPoint: Accelerated Point Searching and Sampling for Neural Renderingcited by 4

50 most cited of 70 All 70 (JSON)