mlsanityData to 14 Oct 2026

Towards High-Fidelity Gaussian Splatting with Queried-Convolution Neural Networks

arXiv 2512.12898 ↗First posted 15 Dec 2025cs.CV cs.GR cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

Gaussian Splatting has revolutionized the field of Novel View Synthesis (NVS) with faster training and real-time rendering. However, its reconstruction fidelity still trails behind the powerful radiance models such as Zip-NeRF. Motivated by our theoretical result that both queries (such as coordinates) and neighborhood are important to learn high-fidelity signals, this paper proposes Queried-Convolutions (Qonvolutions), a simple yet powerful modification using the neighborhood properties of convolution. Qonvolutions convolve a low-fidelity signal with queries to output residual and achieve high-fidelity reconstruction. We empirically demonstrate that combining Gaussian splatting with Qonvolution neural networks (QNNs) results in state-of-the-art NVS on real-world scenes, even outperforming Zip-NeRF on image fidelity. QNNs also enhance performance of 1D regression, 2D regression and 2D super-resolution tasks.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 79 of its 101 references that are in the map. First posted on arXiv 15 Dec 2025.

Builds on

79 of 101 references.

References · 79

  1. 2017Attention Is All You Needcited by 60,361
  2. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
  3. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,177
  4. 20233D Gaussian Splatting for Real-Time Radiance Field Renderingcited by 6,226
  5. 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 6,013
  6. 2022Instant Neural Graphics Primitives with a Multiresolution Hash Encodingcited by 3,723
  7. 2017Progressive Growing of GANs for Improved Quality, Stability, and Variationcited by 2,988
  8. 2019DeepSDF: Learning Continuous Signed Distance Functions for Shape Representationcited by 2,689
  9. 2020Implicit Neural Representations with Periodic Activation Functionscited by 2,238
  10. 2020Fourier Features Let Networks Learn High Frequency Functions in Low Dimensional Domainscited by 2,200
  11. 2021Mip-NeRF 360: Unbounded Anti-Aliased Neural Radiance Fieldscited by 2,032
  12. 2021Mip-NeRF: A Multiscale Representation for Anti-Aliasing Neural Radiance Fieldscited by 1,964
38 more
  1. 2021Plenoxels: Radiance Fields without Neural Networkscited by 1,613
  2. 2021Image Super-Resolution via Iterative Refinementcited by 1,511
  3. 2018On the Spectral Bias of Neural Networkscited by 1,341
  4. 2016Group Equivariant Convolutional Networkscited by 1,165
  5. 2017Deep Image Priorcited by 1,098
  6. 2021Real-ESRGAN: Training Real-World Blind Super-Resolution with Pure Synthetic Datacited by 970
  7. 2023Zip-NeRF: Anti-Aliased Grid-Based Neural Radiance Fieldscited by 671
  8. 2023Mip-Splatting: Alias-free 3D Gaussian Splattingcited by 667
  9. 2023Nerfstudio: A Modular Framework for Neural Radiance Field Developmentcited by 600
  10. 2020Learning Continuous Image Representation with Local Implicit Image Functioncited by 552
  11. 2024CAT3D: Create Anything in 3D with Multi-View Diffusion Modelscited by 432
  12. 2018Recovering Realistic Texture in Image Super-resolution by Deep Spatial Feature Transformcited by 371
  13. 2023ResShift: Efficient Diffusion Model for Image Super-resolution by Residual Shiftingcited by 365
  14. 2020PULSE: Self-Supervised Photo Upsampling via Latent Space Exploration of Generative Modelscited by 358
  15. 2022MobileNeRF: Exploiting the Polygon Rasterization Pipeline for Efficient Neural Field Rendering on Mobile Architecturescited by 311
  16. 2018An Intriguing Failing of Convolutional Neural Networks and the CoordConv Solutioncited by 307
  17. 2024gsplat: An Open-Source Library for Gaussian Splattingcited by 285
  18. 2021Urban Radiance Fieldscited by 263
  19. 2014Understanding image representations by measuring their equivariance and equivalencecited by 243
  20. 2024LVSM: A Large View Synthesis Model with Minimal 3D Inductive Biascited by 189
  21. 2017FSRNet: End-to-End Learning Face Super-Resolution with Facial Priorscited by 170
  22. 2021The Low-Rank Simplicity Bias in Deep Networkscited by 154
  23. 20243D Gaussian Ray Tracing: Fast Tracing of Particle Scenescited by 139
  24. 2024Revising Densification in Gaussian Splattingcited by 128
  25. 2021Local Texture Estimator for Implicit Representation Functioncited by 127
  26. 2024FreGS: 3D Gaussian Splatting with Progressive Frequency Regularizationcited by 105
  27. 2025Cameras as Relative Positional Encodingcited by 105
  28. 2024GES: Generalized Exponential Splatting for Efficient Radiance Field Renderingcited by 92
  29. 2021Learning with invariances in random features and kernel modelscited by 89
  30. 20243DGUT: Enabling Distorted Cameras and Secondary Rays in Gaussian Splattingcited by 88
  31. 2023FINER: Flexible spectral-bias tuning in Implicit NEural Representation by Variable-periodic Activation Functionscited by 78
  32. 2023Adaptive Shells for Efficient Neural Radiance Field Renderingcited by 69
  33. 2019A Fine-Grained Spectral Perspective on Neural Networkscited by 68
  34. 2023GAvatar: Animatable 3D Gaussian Avatars with Implicit Mesh Learningcited by 63
  35. 2023Multi-stage Neural Networks: Function Approximator of Machine Precisioncited by 48
  36. 2024EVER: Exact Volumetric Ellipsoid Rendering for Real-time View Synthesiscited by 48
  37. 20243D-HGS: 3D Half-Gaussian Splattingcited by 44
  38. 2024Neural Redshift: Random Networks are not Random Functionscited by 43

50 most cited of 79 All 79 (JSON)

Built on by

Not cited yet.