FreeNeRF: Improving Few-Shot Neural Rendering with Free Frequency Regularization
Authors:
Top Cited Papers
- 1 June 2023
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 8254-8263
Abstract
Novel view synthesis with sparse inputs is a challenging problem for neural radiance fields (NeRF). Recent efforts alleviate this challenge by introducing external supervision, such as pre-trained models and extra depth signals, or by using non-trivial patch-based rendering. In this paper, we present Frequency regularized NeRF (FreeNeRF), a surprisingly simple baseline that outperforms previous methods with minimal modifications to plain NeRF. We analyze the key challenges in few-shot neural rendering and find that frequency plays an important role in NeRF's training. Based on this analysis, we propose two regularization terms: one to regularize the frequency range of NeRF's inputs, and the other to penalize the near-camera density fields. Both techniques are “free lunches” that come at no additional computational cost. We demonstrate that even with just one line of code change, the original NeRF can achieve similar performance to other complicated methods in the few-shot setting. FreeNeRF achieves state-of-the-art performance across diverse datasets, including Blender, DTU, and LLFF. We hope that this simple baseline will motivate a rethinking of the fundamental role of frequency in NeRF's training, under both the low-data regime and beyond. This project is released at FreeNeRF.Keywords
All Related Versions
This publication has 19 references indexed in Scilit:
- NerfingMVS: Guided Optimization of Neural Radiance Fields for Indoor Multi-view Stereo2021
- Putting NeRF on a Diet: Semantically Consistent Few-Shot View Synthesis2021
- MVSNeRF: Fast Generalizable Radiance Field Reconstruction from Multi-View Stereo2021
- BARF: Bundle-Adjusting Neural Radiance Fields2021
- Neural Body: Implicit Neural Representations with Structured Latent Codes for Novel View Synthesis of Dynamic Humans2021
- Stereo Radiance Fields (SRF): Learning View Synthesis for Sparse Views of Novel Scenes2021
- pixelNeRF: Neural Radiance Fields from One or Few Images2021
- Neural volumesACM Transactions on Graphics, 2019
- Local light field fusionACM Transactions on Graphics, 2019
- Large Scale Multi-view Stereopsis Evaluation2014