# NeRFLiX: High-Quality Neural View Synthesis by Learning a Degradation-Driven Inter-viewpoint MiXer

arXiv: https://arxiv.org/abs/2303.06919 · HTML: https://mlsanity.com/paper/2303.06919/

## Key facts

- Cited by 29 papers in the map (data through 14 Oct 2026).
- Builds on 72 of its 87 references that are in the map.
- First posted on arXiv 13 Mar 2023.

## Builds on (most cited first, 30 of 72)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [Rethinking the Inception Architecture for Computer Vision](https://mlsanity.com/paper/1512.00567/) (2015)
- [Instant Neural Graphics Primitives with a Multiresolution Hash Encoding](https://mlsanity.com/paper/2201.05989/) (2022)
- [RAFT: Recurrent All-Pairs Field Transforms for Optical Flow](https://mlsanity.com/paper/2003.12039/) (2020)
- [Mip-NeRF: A Multiscale Representation for Anti-Aliasing Neural Radiance Fields](https://mlsanity.com/paper/2103.13415/) (2021)
- [SwinIR: Image Restoration Using Swin Transformer](https://mlsanity.com/paper/2108.10257/) (2021)
- [Plenoxels: Radiance Fields without Neural Networks](https://mlsanity.com/paper/2112.05131/) (2021)
- [Deformable Convolutional Networks](https://mlsanity.com/paper/1703.06211/) (2017)
- [D-NeRF: Neural Radiance Fields for Dynamic Scenes](https://mlsanity.com/paper/2011.13961/) (2020)
- [TensoRF: Tensorial Radiance Fields](https://mlsanity.com/paper/2203.09517/) (2022)
- [ESRGAN: Enhanced Super-Resolution Generative Adversarial Networks](https://mlsanity.com/paper/1809.00219/) (2018)
- [NeRF in the Wild: Neural Radiance Fields for Unconstrained Photo Collections](https://mlsanity.com/paper/2008.02268/) (2020)
- [Image Super-Resolution Using Deep Convolutional Networks](https://mlsanity.com/paper/1501.00092/) (2014)
- [Nerfies: Deformable Neural Radiance Fields](https://mlsanity.com/paper/2011.12948/) (2020)
- [Video Swin Transformer](https://mlsanity.com/paper/2106.13230/) (2021)
- [Real-ESRGAN: Training Real-World Blind Super-Resolution with Pure Synthetic Data](https://mlsanity.com/paper/2107.10833/) (2021)
- [Direct Voxel Grid Optimization: Super-fast Convergence for Radiance Fields Reconstruction](https://mlsanity.com/paper/2111.11215/) (2021)
- [PlenOctrees for Real-time Rendering of Neural Radiance Fields](https://mlsanity.com/paper/2103.14024/) (2021)
- [NeRF++: Analyzing and Improving Neural Radiance Fields](https://mlsanity.com/paper/2010.07492/) (2020)
- [Residual Dense Network for Image Super-Resolution](https://mlsanity.com/paper/1802.08797/) (2018)
- [MVSNeRF: Fast Generalizable Radiance Field Reconstruction from Multi-View Stereo](https://mlsanity.com/paper/2103.15595/) (2021)
- [Depth-supervised NeRF: Fewer Views and Faster Training for Free](https://mlsanity.com/paper/2107.02791/) (2021)
- [Block-NeRF: Scalable Large Scene Neural View Synthesis](https://mlsanity.com/paper/2202.05263/) (2022)
- [IBRNet: Learning Multi-View Image-Based Rendering](https://mlsanity.com/paper/2102.13090/) (2021)
- [KiloNeRF: Speeding up Neural Radiance Fields with Thousands of Tiny MLPs](https://mlsanity.com/paper/2103.13744/) (2021)
- [Local Light Field Fusion: Practical View Synthesis with Prescriptive Sampling Guidelines](https://mlsanity.com/paper/1905.00889/) (2019)
- [BARF: Bundle-Adjusting Neural Radiance Fields](https://mlsanity.com/paper/2104.06405/) (2021)
- [Video Enhancement with Task-Oriented Flow](https://mlsanity.com/paper/1711.09078/) (2017)
- [RegNeRF: Regularizing Neural Radiance Fields for View Synthesis from Sparse Inputs](https://mlsanity.com/paper/2112.00724/) (2021)

## Built on by (most cited first, 29 of 29)

- [GEN3C: 3D-Informed World-Consistent Video Generation with Precise Camera Control](https://mlsanity.com/paper/2503.03751/) (2025)
- [Difix3D+: Improving 3D Reconstructions with Single-Step Diffusion Models](https://mlsanity.com/paper/2503.01774/) (2025)
- [A Survey on All-in-One Image Restoration: Taxonomy, Evaluation and Future Trends](https://mlsanity.com/paper/2410.15067/) (2024)
- [SWinGS: Sliding Windows for Dynamic 3D Gaussian Splatting](https://mlsanity.com/paper/2312.13308/) (2023)
- [GANeRF: Leveraging Discriminators to Optimize Neural Radiance Fields](https://mlsanity.com/paper/2306.06044/) (2023)
- [RealX3D: A Physically-Degraded 3D Benchmark for Multi-view Visual Restoration and Reconstruction](https://mlsanity.com/paper/2512.23437/) (2025)
- [SC-NeRF: Self-Correcting Neural Radiance Field with Sparse Views](https://mlsanity.com/paper/2309.05028/) (2023)
- [Neural Radiance Field-based Visual Rendering: A Comprehensive Review](https://mlsanity.com/paper/2404.00714/) (2024)
- [Neural Radiance Fields for the Real World: A Survey](https://mlsanity.com/paper/2501.13104/) (2025)
- [From NeRFLiX to NeRFLiX++: A General NeRF-Agnostic Restorer Paradigm](https://mlsanity.com/paper/2306.06388/) (2023)
- [LookCloser: Frequency-aware Radiance Field for Tiny-Detail Scene](https://mlsanity.com/paper/2503.18513/) (2025)
- [Dynamic NeRFs for Soccer Scenes](https://mlsanity.com/paper/2309.06802/) (2023)
- [RaFE: Generative Radiance Fields Restoration](https://mlsanity.com/paper/2404.03654/) (2024)
- [MaRINeR: Enhancing Novel Views by Matching Rendered Images with Nearby References](https://mlsanity.com/paper/2407.13745/) (2024)
- [PBR-SR: Mesh PBR Texture Super Resolution from 2D Image Priors](https://mlsanity.com/paper/2506.02846/) (2025)
- [OmniView: An All-Seeing Diffusion Model for 3D and 4D View Synthesis](https://mlsanity.com/paper/2512.10940/) (2025)
- [RustNeRF: Robust Neural Radiance Field with Low-Quality Images](https://mlsanity.com/paper/2401.03257/) (2024)
- [RoGUENeRF: A Robust Geometry-Consistent Universal Enhancer for NeRF](https://mlsanity.com/paper/2403.11909/) (2024)
- [SR-NeRV: Improving Embedding Efficiency of Neural Video Representation via Super-Resolution](https://mlsanity.com/paper/2505.00046/) (2025)
- [Geometry-Aware Single-Image 4D Synthesis via Dense Trajectory Generation](https://mlsanity.com/paper/2512.05044/) (2025)
- [3D Reconstruction and New View Synthesis of Indoor Environments based on a Dual Neural Radiance Field](https://mlsanity.com/paper/2401.14726/) (2024)
- [Drantal-NeRF: Diffusion-Based Restoration for Anti-aliasing Neural Radiance Field](https://mlsanity.com/paper/2407.07461/) (2024)
- [Non-Aligned Reference Image Quality Assessment for Novel View Synthesis](https://mlsanity.com/paper/2511.08155/) (2025)
- [DenoiseGS: Gaussian Reconstruction Model for Burst Denoising](https://mlsanity.com/paper/2511.22939/) (2025)
- [CompSplat: Compression-aware 3D Gaussian Splatting for Real-world Video](https://mlsanity.com/paper/2602.09816/) (2026)
- [Survey on Controlable Image Synthesis with Deep Learning](https://mlsanity.com/paper/2307.10275/) (2023)
- [GMT: Enhancing Generalizable Neural Rendering via Geometry-Driven Multi-Reference Texture Transfer](https://mlsanity.com/paper/2410.00672/) (2024)
- [CRAYM: Neural Field Optimization via Camera RAY Matching](https://mlsanity.com/paper/2412.01618/) (2024)
- [Rethinking 3D Noise: Learning 3D-Aware Video Priors via Optimization-Free Morphological Perturbations](https://mlsanity.com/paper/2609.03657/) (2026)

## Abstract (arXiv)

Neural radiance fields (NeRF) show great success in novel view synthesis. However, in real-world scenes, recovering high-quality details from the source images is still challenging for the existing NeRF-based approaches, due to the potential imperfect calibration information and scene representation inaccuracy. Even with high-quality training frames, the synthetic novel views produced by NeRF models still suffer from notable rendering artifacts, such as noise, blur, etc. Towards to improve the synthesis quality of NeRF-based approaches, we propose NeRFLiX, a general NeRF-agnostic restorer paradigm by learning a degradation-driven inter-viewpoint mixer. Specially, we design a NeRF-style degradation modeling approach and construct large-scale training data, enabling the possibility of effectively removing NeRF-native rendering artifacts for existing deep neural networks. Moreover, beyond the degradation removal, we propose an inter-viewpoint aggregation framework that is able to fuse highly related high-quality training images, pushing the performance of cutting-edge NeRF models to entirely new levels and producing highly photo-realistic synthetic views.