Research Paper Analysis

Purpose

Here will be the analysis's of potential papers to integrate into the backend of our project. Since the focus of this project is to get NeRF working in a web app, the most relevant factors are open license, computational resources, robustness to real world data. Breaking this down further these are the most important qualities ranked:

1. Source code is available and fully open source

• Open source licenses are licenses that comply with the Open Source Definition

2. Speed and memory use in training should be low enough to allow for ease of development

• Sub hour NeRF training time
• Less then 8GB memory consumption
• Not reliant on custom kernels or specific GPU models

3. Inference speed should be fast enough to allow for video rendering

• Inference of at least 1 fps

4. Robustness to real world data

• Quality should be on par or better then the original NeRF paper
• Should work with SFM techniques
• Insensitive to depth inaccuracies or image artifacts

List of potential project papers

• MVSNeRF: Fast Generalizable Radiance Field Reconstruction from Multi-View Stereo
• FastNeRF: High-Fidelity Neural Rendering at 200FPS
• SqueezeNeRF: Further factorized FastNeRF for memory-efficient inference
• EfficientNeRF: Efficient Neural Radiance Field
• Fast Dynamic Radiance Fields with Time-Aware Neural Voxels
• TensoRF: Tensorial Radiance Fields