MomentsNeRF: Leveraging Orthogonal Moments for Few-Shot Neural Rendering
Not on the map. Why?
Abstract (arXiv)
We propose MomentsNeRF, a novel framework for one- and few-shot neural rendering that predicts a neural representation of a 3D scene using Orthogonal Moments. Our architecture offers a new transfer learning method to train on multi-scenes and incorporate a per-scene optimization using one or a few images at test time. Our approach is the first to successfully harness features extracted from Gabor and Zernike moments, seamlessly integrating them into the NeRF architecture. We show that MomentsNeRF performs better in synthesizing images with complex textures and shapes, achieving a significant noise reduction, artifact elimination, and completing the missing parts compared to the recent one- and few-shot neural rendering frameworks. Extensive experiments on the DTU and Shapenet datasets show that MomentsNeRF improves the state-of-the-art by 3.39;dB;PSNR, 11.1% SSIM, 17.9% LPIPS, and 8.3% DISTS metrics. Moreover, it outperforms state-of-the-art performance for both novel view synthesis and single-image 3D view reconstruction. The source code is accessible at: https://amughrabi.github.io/momentsnerf/.
Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 55 of its 72 references that are in the map. First posted on arXiv 2 Jul 2024.
Builds on
55 of 72 references.
References · 55
- 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,029
- 2022Instant Neural Graphics Primitives with a Multiresolution Hash Encodingcited by 3,698
- 2022DreamFusion: Text-to-3D using 2D Diffusioncited by 3,006
- 2015ShapeNet: An Information-Rich 3D Model Repositorycited by 2,880
- 2021Mip-NeRF: A Multiscale Representation for Anti-Aliasing Neural Radiance Fieldscited by 1,957
- 2020pixelNeRF: Neural Radiance Fields from One or Few Imagescited by 1,574
- 2020D-NeRF: Neural Radiance Fields for Dynamic Scenescited by 1,459
- 2022Magic3D: High-Resolution Text-to-3D Content Creationcited by 1,285
- 2020NeRF in the Wild: Neural Radiance Fields for Unconstrained Photo Collectionscited by 1,230
- 2020Nerfies: Deformable Neural Radiance Fieldscited by 1,194
- 2020Image Quality Assessment: Unifying Structure and Texture Similaritycited by 792
- 2021MVSNeRF: Fast Generalizable Radiance Field Reconstruction from Multi-View Stereocited by 735
38 more
- 2021Depth-supervised NeRF: Fewer Views and Faster Training for Freecited by 732
- 2021RegNeRF: Regularizing Neural Radiance Fields for View Synthesis from Sparse Inputscited by 614
- 2021Neural Fields in Visual Computing and Beyondcited by 539
- 2021Zero-Shot Text-Guided Object Generation with Dream Fieldscited by 513
- 2022Latent-NeRF for Shape-Guided Generation of 3D Shapes and Texturescited by 506
- 2021Putting NeRF on a Diet: Semantically Consistent Few-Shot View Synthesiscited by 464
- 2023Neuralangelo: High-Fidelity Neural Surface Reconstructioncited by 464
- 2015Recent Advances in Convolutional Neural Networkscited by 360
- 2023FreeNeRF: Improving Few-shot Neural Rendering with Free Frequency Regularizationcited by 310
- 2022MobileNeRF: Exploiting the Polygon Rasterization Pipeline for Efficient Neural Field Rendering on Mobile Architecturescited by 308
- 2021Dense Depth Priors for Neural Radiance Fields from Sparse Input Viewscited by 301
- 2022DynIBaR: Neural Dynamic Image-Based Renderingcited by 224
- 2022SPARF: Neural Radiance Fields from Sparse and Noisy Posescited by 195
- 2021Stereo Radiance Fields (SRF): Learning View Synthesis for Sparse Views of Novel Scenescited by 190
- 2022Panoptic Lifting for 3D Scene Understanding with Neural Fieldscited by 171
- 2022NeRDi: Single-View NeRF Synthesis with Language-Guided Diffusion as General Image Priorscited by 156
- 2021Beyond Periodicity: Towards a Unifying Framework for Activations in Coordinate-MLPscited by 134
- 2023F2-NeRF: Fast Neural Radiance Field Training with Free Camera Trajectoriescited by 118
- 2022Vision Transformer for NeRF-Based View Synthesis from a Single Input Imagecited by 104
- 2023RobustNeRF: Ignoring Distractors with Robust Lossescited by 101
- 2023SINE: Semantic-driven Image-based NeRF Editing with Prior-guided Editing Fieldcited by 93
- 2023StyleRF: Zero-shot 3D Style Transfer of Neural Radiance Fieldscited by 79
- 2022Pix2NeRF: Unsupervised Conditional π-GAN for Single Image to Neural Radiance Fields Translationcited by 73
- 2023Learning Neural Volumetric Representations of Dynamic Humans in Minutescited by 70
- 2022DisCoScene: Spatially Disentangled Generative Radiance Fields for Controllable 3D-aware Scene Synthesiscited by 61
- 2017Gabor Convolutional Networkscited by 55
- 2023Nerflets: Local Radiance Fields for Efficient Structure-Aware 3D Scene Representation from 2D Supervisioncited by 44
- 2023Flow supervision for Deformable NeRFcited by 42
- 2022Ref-NPR: Reference-Based Non-Photorealistic Radiance Fields for Controllable Scene Stylizationcited by 35
- 2023SCADE: NeRFs from Space Carving with Ambiguity-Aware Depth Estimatescited by 35
- 2022Shape, Pose, and Appearance from a Single Image via Bootstrapped Radiance Field Inversioncited by 30
- 2022EditableNeRF: Editing Topologically Varying Neural Radiance Fields by Key Pointscited by 30
- 2023Learning Neural Duplex Radiance Fields for Real-Time View Synthesiscited by 28
- 2022NeRFInvertor: High Fidelity NeRF-GAN Inversion for Single-shot Real Image Animationcited by 23
- 2019GaborNet: Gabor filters with learnable parameters in deep convolutional neural networkscited by 17
- 2022Exact-NeRF: An Exploration of a Precise Volumetric Parameterization for Neural Radiance Fieldscited by 15
- 2023FlexNeRF: Photorealistic Free-viewpoint Rendering of Moving Humans from Sparse Viewscited by 15
- 2022GazeNeRF: 3D-Aware Gaze Redirection with Neural Radiance Fieldscited by 12
50 most cited of 55 All 55 (JSON)
Built on by
Citing papers per year: 2026: 2.
2 papers.