# PERF: Performant, Explicit Radiance Fields

arXiv: https://arxiv.org/abs/2112.05598 · HTML: https://mlsanity.com/paper/2112.05598/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 32 references that are in the map.
- First posted on arXiv 10 Dec 2021.

## Builds on (most cited first, 20 of 20)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [ShapeNet: An Information-Rich 3D Model Repository](https://mlsanity.com/paper/1512.03012/) (2015)
- [Fourier Features Let Networks Learn High Frequency Functions in Low Dimensional Domains](https://mlsanity.com/paper/2006.10739/) (2020)
- [NeRF in the Wild: Neural Radiance Fields for Unconstrained Photo Collections](https://mlsanity.com/paper/2008.02268/) (2020)
- [Neural Sparse Voxel Fields](https://mlsanity.com/paper/2007.11571/) (2020)
- [PlenOctrees for Real-time Rendering of Neural Radiance Fields](https://mlsanity.com/paper/2103.14024/) (2021)
- [MVSNet: Depth Inference for Unstructured Multi-view Stereo](https://mlsanity.com/paper/1804.02505/) (2018)
- [MVSNeRF: Fast Generalizable Radiance Field Reconstruction from Multi-View Stereo](https://mlsanity.com/paper/2103.15595/) (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)
- [FastNeRF: High-Fidelity Neural Rendering at 200FPS](https://mlsanity.com/paper/2103.10380/) (2021)
- [Baking Neural Radiance Fields for Real-Time View Synthesis](https://mlsanity.com/paper/2103.14645/) (2021)
- [State of the Art on Neural Rendering](https://mlsanity.com/paper/2004.03805/) (2020)
- [Recurrent MVSNet for High-resolution Multi-view Stereo Depth Inference](https://mlsanity.com/paper/1902.10556/) (2019)
- [Learned Initializations for Optimizing Coordinate-Based Neural Representations](https://mlsanity.com/paper/2012.02189/) (2020)
- [DONeRF: Towards Real-Time Rendering of Compact Neural Radiance Fields using Depth Oracle Networks](https://mlsanity.com/paper/2103.03231/) (2021)
- [Stereo Magnification: Learning View Synthesis using Multiplane Images](https://mlsanity.com/paper/1805.09817/) (2018)
- [Neural Volumes: Learning Dynamic Renderable Volumes from Images](https://mlsanity.com/paper/1906.07751/) (2019)
- [DeRF: Decomposed Radiance Fields](https://mlsanity.com/paper/2011.12490/) (2020)
- [A Survey of Structure from Motion](https://mlsanity.com/paper/1701.08493/) (2017)

## Built on by (most cited first, 5 of 5)

- [3DGS-LM: Faster Gaussian-Splatting Optimization with Levenberg-Marquardt](https://mlsanity.com/paper/2409.12892/) (2024)
- [3DGS2: Near Second-order Converging 3D Gaussian Splatting](https://mlsanity.com/paper/2501.13975/) (2025)
- [One is All: Bridging the Gap Between Neural Radiance Fields Architectures with Progressive Volume Distillation](https://mlsanity.com/paper/2211.15977/) (2022)
- [Progressive Volume Distillation with Active Learning for Efficient NeRF Architecture Conversion](https://mlsanity.com/paper/2304.04012/) (2023)
- [Addressing the Shape-Radiance Ambiguity in View-Dependent Radiance Fields](https://mlsanity.com/paper/2203.01553/) (2022)

## Abstract (arXiv)

We present a novel way of approaching image-based 3D reconstruction based on radiance fields. The problem of volumetric reconstruction is formulated as a non-linear least-squares problem and solved explicitly without the use of neural networks. This enables the use of solvers with a higher rate of convergence than what is typically used for neural networks, and fewer iterations are required until convergence. The volume is represented using a grid of voxels, with the scene surrounded by a hierarchy of environment maps. This makes it possible to get clean reconstructions of 360deg scenes where the foreground and background is separated. A number of synthetic and real scenes from well known benchmark-suites are successfully reconstructed with quality on par with state-of-the-art methods, but at significantly reduced reconstruction times.