mlsanityData to 7 Oct 2026

InfoNeRF: Ray Entropy Minimization for Few-Shot Neural Volume Rendering

arXiv 2112.15399 ↗First posted 31 Dec 2021cs.CV cs.GR eess.IVcited by 180

Not on the map. Why?

Abstract (arXiv)

We present an information-theoretic regularization technique for few-shot novel view synthesis based on neural implicit representation. The proposed approach minimizes potential reconstruction inconsistency that happens due to insufficient viewpoints by imposing the entropy constraint of the density in each ray. In addition, to alleviate the potential degenerate issue when all training images are acquired from almost redundant viewpoints, we further incorporate the spatially smoothness constraint into the estimated images by restricting information gains from a pair of rays with slightly different viewpoints. The main idea of our algorithm is to make reconstructed scenes compact along individual rays and consistent across rays in the neighborhood. The proposed regularizers can be plugged into most of existing neural volume rendering techniques based on NeRF in a straightforward way. Despite its simplicity, we achieve consistently improved performance compared to existing neural view synthesis methods by large margins on multiple standard benchmarks.

Key facts. Cited by 180 papers in the map (data through 7 Oct 2026). Builds on 23 of its 42 references that are in the map. First posted on arXiv 31 Dec 2021.

Builds on

23 of 42 references.

References · 23

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  3. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,029
  4. 2015Rethinking the Inception Architecture for Computer Visioncited by 5,451
  5. 2021Mip-NeRF: A Multiscale Representation for Anti-Aliasing Neural Radiance Fieldscited by 1,957
  6. 2020pixelNeRF: Neural Radiance Fields from One or Few Imagescited by 1,574
  7. 2018Demystifying MMD GANscited by 1,268
  8. 2021PlenOctrees for Real-time Rendering of Neural Radiance Fieldscited by 904
  9. 2019PIFu: Pixel-Aligned Implicit Function for High-Resolution Clothed Human Digitizationcited by 818
  10. 2020Neural Scene Flow Fields for Space-Time View Synthesis of Dynamic Scenescited by 750
  11. 2021Depth-supervised NeRF: Fewer Views and Faster Training for Freecited by 732
  12. 2020Neural Body: Implicit Neural Representations with Structured Latent Codes for Novel View Synthesis of Dynamic Humanscited by 634
11 more
  1. 2020NeRV: Neural Reflectance and Visibility Fields for Relighting and View Synthesiscited by 493
  2. 2021Putting NeRF on a Diet: Semantically Consistent Few-Shot View Synthesiscited by 464
  3. 2020Single-View View Synthesis with Multiplane Imagescited by 263
  4. 2019DeepView: View Synthesis with Learned Gradient Descentcited by 253
  5. 2021NeX: Real-time View Synthesis with Neural Basis Expansioncited by 215
  6. 2018Stereo Magnification: Learning View Synthesis using Multiplane Imagescited by 206
  7. 2015DeepStereo: Learning to Predict New Views from the World's Imagerycited by 185
  8. 2016View Synthesis by Appearance Flowcited by 172
  9. 2021Neural Human Performer: Learning Generalizable Radiance Fields for Human Performance Renderingcited by 158
  10. 2021NeRF--: Neural Radiance Fields Without Known Camera Parameterscited by 155
  11. 2017Learning to Synthesize a 4D RGBD Light Field from a Single Imagecited by 60

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 12; 2023: 58; 2024: 66; 2025: 34; 2026: 10.

180 papers.

Sort:

By area:

  1. 2023Magic123: One Image to High-Quality 3D Object Generation Using Both 2D and 3D Diffusion Priorscited by 395
  2. 2024DNGaussian: Optimizing Sparse-View 3D Gaussian Radiance Fields with Global-Local Depth Normalizationcited by 256
  3. 2023SparseNeRF: Distilling Depth Ranking for Few-shot Novel View Synthesiscited by 247
  4. 2022NoPe-NeRF: Optimising Neural Radiance Field with No Pose Priorcited by 235
  5. 2022SPARF: Neural Radiance Fields from Sparse and Noisy Posescited by 195
  6. 2023COLMAP-Free 3D Gaussian Splattingcited by 193
  7. 2023Depth-Regularized Optimization for 3D Gaussian Splatting in Few-Shot Imagescited by 172
  8. 2022SinNeRF: Training Neural Radiance Fields on Complex Scenes from a Single Imagecited by 165
  9. 2023PF-LRM: Pose-Free Large Reconstruction Model for Joint Pose and Shape Predictioncited by 165
  10. 2025The Unreasonable Effectiveness of Entropy Minimization in LLM Reasoningcited by 160
  11. 2022D2NeRF: Self-Supervised Decoupling of Dynamic and Static Objects from a Monocular Videocited by 136
  12. 2024CoR-GS: Sparse-View 3D Gaussian Splatting via Co-Regularizationcited by 120
38 more
  1. 2024GES: Generalized Exponential Splatting for Efficient Radiance Field Renderingcited by 92
  2. 2024Fully Explicit Dynamic Gaussian Splattingcited by 75
  3. 2022Removing Objects From Neural Radiance Fieldscited by 66
  4. 2023Behind the Scenes: Density Fields for Single View Reconstructioncited by 63
  5. 2024BAD-Gaussians: Bundle Adjusted Deblur Gaussian Splattingcited by 61
  6. 2024PF3plat: Pose-Free Feed-Forward 3D Gaussian Splattingcited by 60
  7. 2023Factor Fields: A Unified Framework for Neural Fields and Beyondcited by 58
  8. 2023GeCoNeRF: Few-shot Neural Radiance Fields via Geometric Consistencycited by 54
  9. 20243D Convex Splatting: Radiance Field Rendering with 3D Smooth Convexescited by 50
  10. 20233D generation on ImageNetcited by 47
  11. 2023LiDAR-NeRF: Novel LiDAR View Synthesis via Neural Radiance Fieldscited by 46
  12. 2023Control3D: Towards Controllable Text-to-3D Generationcited by 46
  13. 2024Generic 3D Diffusion Adapter Using Controlled Multi-View Editingcited by 46
  14. 2023PERF: Panoramic Neural Radiance Field from a Single Panoramacited by 45
  15. 2023SimpleNeRF: Regularizing Sparse Input Neural Radiance Fields with Simpler Solutionscited by 44
  16. 2023Robust e-NeRF: NeRF from Sparse & Noisy Events under Non-Uniform Motioncited by 44
  17. 2024PhyRecon: Physically Plausible Neural Scene Reconstructioncited by 44
  18. 2023ViP-NeRF: Visibility Prior for Sparse Input Neural Radiance Fieldscited by 43
  19. 2024Binocular-Guided 3D Gaussian Splatting with View Consistency for Sparse View Synthesiscited by 41
  20. 2023MixNeRF: Modeling a Ray with Mixture Density for Novel View Synthesis from Sparse Inputscited by 40
  21. 2023Deceptive-NeRF/3DGS: Diffusion-Generated Pseudo-Observations for High-Quality Sparse-View Reconstructioncited by 39
  22. 2022Fast Learning Radiance Fields by Shooting Much Fewer Rayscited by 38
  23. 2023NeuSurf: On-Surface Priors for Neural Surface Reconstruction from Sparse Input Viewscited by 36
  24. 2024SpaRP: Fast 3D Object Reconstruction and Pose Estimation from Sparse Viewscited by 35
  25. 2025Decompositional Neural Scene Reconstruction with Generative Diffusion Priorcited by 30
  26. 2023FlipNeRF: Flipped Reflection Rays for Few-shot Novel View Synthesiscited by 29
  27. 2024MVPGS: Excavating Multi-view Priors for Gaussian Splatting from Sparse Input Viewscited by 29
  28. 2025Taming Video Diffusion Prior with Scene-Grounding Guidance for 3D Gaussian Splatting from Sparse Inputscited by 29
  29. 2022StructNeRF: Neural Radiance Fields for Indoor Scenes with Structural Hintscited by 28
  30. 2023ScatterNeRF: Seeing Through Fog with Physically-Based Inverse Neural Renderingcited by 28
  31. 20244D Gaussian Splatting in the Wild with Uncertainty-Aware Regularizationcited by 28
  32. 2025FlowR: Flowing from Sparse to Dense 3D Reconstructionscited by 28
  33. 2022ParticleNeRF: A Particle-Based Encoding for Online Neural Radiance Fieldscited by 27
  34. 2023DaRF: Boosting Radiance Fields from Sparse Inputs with Monocular Depth Adaptationcited by 25
  35. 2023ZeroRF: Fast Sparse View 360deg Reconstruction with Zero Pretrainingcited by 24
  36. 2025LongSplat: Robust Unposed 3D Gaussian Splatting for Casual Long Videoscited by 23
  37. 2023PanoGRF: Generalizable Spherical Radiance Fields for Wide-baseline Panoramascited by 22
  38. 2024SparseCraft: Few-Shot Neural Reconstruction through Stereopsis Guided Geometric Linearizationcited by 19

50 most cited of 180 All 180 (JSON)