# HERO: Hardware-Efficient RL-based Optimization Framework for NeRF Quantization

arXiv: https://arxiv.org/abs/2510.09010 · HTML: https://mlsanity.com/paper/2510.09010/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 8 of its 16 references that are in the map.
- First posted on arXiv 10 Oct 2025.

## Builds on (most cited first, 8 of 8)

- [Instant Neural Graphics Primitives with a Multiresolution Hash Encoding](https://mlsanity.com/paper/2201.05989/) (2022)
- [Direct Voxel Grid Optimization: Super-fast Convergence for Radiance Fields Reconstruction](https://mlsanity.com/paper/2111.11215/) (2021)
- [HAQ: Hardware-Aware Automated Quantization with Mixed Precision](https://mlsanity.com/paper/1811.08886/) (2018)
- [LSQ+: Improving low-bit quantization through learnable offsets and better initialization](https://mlsanity.com/paper/2004.09576/) (2020)
- [Compressing Volumetric Radiance Fields to 1 MB](https://mlsanity.com/paper/2211.16386/) (2022)
- [Instant-3D: Instant Neural Radiance Field Training Towards On-Device AR/VR 3D Reconstruction](https://mlsanity.com/paper/2304.12467/) (2023)
- [Content-Aware Radiance Fields: Aligning Model Complexity with Scene Intricacy Through Learned Bitwidth Quantization](https://mlsanity.com/paper/2410.19483/) (2024)
- [SpNeRF: Memory Efficient Sparse Volumetric Neural Rendering Accelerator for Edge Devices](https://mlsanity.com/paper/2505.08191/) (2025)

## Built on by (most cited first, 1 of 1)

- [3DTurboQuant: Training-Free Near-Optimal Quantization for 3D Reconstruction Models](https://mlsanity.com/paper/2604.05366/) (2026)

## Abstract (arXiv)

Neural Radiance Field (NeRF) has emerged as a promising 3D reconstruction method, delivering high-quality results for AR/VR applications. While quantization methods and hardware accelerators have been proposed to enhance NeRF's computational efficiency, existing approaches face crucial limitations. Current quantization methods operate without considering hardware architecture, resulting in sub-optimal solutions within the vast design space encompassing accuracy, latency, and model size. Additionally, existing NeRF accelerators heavily rely on human experts to explore this design space, making the optimization process time-consuming, inefficient, and unlikely to discover optimal solutions. To address these challenges, we introduce HERO, a reinforcement learning framework performing hardware-aware quantization for NeRF. Our framework integrates a NeRF accelerator simulator to generate real-time hardware feedback, enabling fully automated adaptation to hardware constraints. Experimental results demonstrate that HERO achieves 1.31-1.33 × better latency, 1.29-1.33 × improved cost efficiency, and a more compact model size compared to CAQ, a previous state-of-the-art NeRF quantization framework. These results validate our framework's capability to effectively navigate the complex design space between hardware and algorithm requirements, discovering superior quantization policies for NeRF implementation. Code is available at https://github.com/ypzhng/HERO.