# HollowNeRF: Pruning Hashgrid-Based NeRFs with Trainable Collision Mitigation

arXiv: https://arxiv.org/abs/2308.10122 · HTML: https://mlsanity.com/paper/2308.10122/

## Key facts

- Cited by 16 papers in the map (data through 14 Oct 2026).
- Builds on 27 of its 35 references that are in the map.
- First posted on arXiv 19 Aug 2023.

## Builds on (most cited first, 27 of 27)

- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [Instant Neural Graphics Primitives with a Multiresolution Hash Encoding](https://mlsanity.com/paper/2201.05989/) (2022)
- [Mip-NeRF 360: Unbounded Anti-Aliased Neural Radiance Fields](https://mlsanity.com/paper/2111.12077/) (2021)
- [Mip-NeRF: A Multiscale Representation for Anti-Aliasing Neural Radiance Fields](https://mlsanity.com/paper/2103.13415/) (2021)
- [Plenoxels: Radiance Fields without Neural Networks](https://mlsanity.com/paper/2112.05131/) (2021)
- [TensoRF: Tensorial Radiance Fields](https://mlsanity.com/paper/2203.09517/) (2022)
- [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)
- [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)
- [KiloNeRF: Speeding up Neural Radiance Fields with Thousands of Tiny MLPs](https://mlsanity.com/paper/2103.13744/) (2021)
- [RegNeRF: Regularizing Neural Radiance Fields for View Synthesis from Sparse Inputs](https://mlsanity.com/paper/2112.00724/) (2021)
- [Ref-NeRF: Structured View-Dependent Appearance for Neural Radiance Fields](https://mlsanity.com/paper/2112.03907/) (2021)
- [Point-NeRF: Point-based Neural Radiance Fields](https://mlsanity.com/paper/2201.08845/) (2022)
- [Baking Neural Radiance Fields for Real-Time View Synthesis](https://mlsanity.com/paper/2103.14645/) (2021)
- [Putting NeRF on a Diet: Semantically Consistent Few-Shot View Synthesis](https://mlsanity.com/paper/2104.00677/) (2021)
- [Mega-NeRF: Scalable Construction of Large-Scale NeRFs for Virtual Fly-Throughs](https://mlsanity.com/paper/2112.10703/) (2021)
- [Extracting Triangular 3D Models, Materials, and Lighting From Images](https://mlsanity.com/paper/2111.12503/) (2021)
- [NeRF in the Dark: High Dynamic Range View Synthesis from Noisy Raw Images](https://mlsanity.com/paper/2111.13679/) (2021)
- [DONeRF: Towards Real-Time Rendering of Compact Neural Radiance Fields using Depth Oracle Networks](https://mlsanity.com/paper/2103.03231/) (2021)
- [BungeeNeRF: Progressive Neural Radiance Field for Extreme Multi-scale Scene Rendering](https://mlsanity.com/paper/2112.05504/) (2021)
- [NeRFReN: Neural Radiance Fields with Reflections](https://mlsanity.com/paper/2111.15234/) (2021)
- [NeRF for Outdoor Scene Relighting](https://mlsanity.com/paper/2112.05140/) (2021)
- [Compressible-composable NeRF via Rank-residual Decomposition](https://mlsanity.com/paper/2205.14870/) (2022)
- [AdaNeRF: Adaptive Sampling for Real-time Rendering of Neural Radiance Fields](https://mlsanity.com/paper/2207.10312/) (2022)
- [Differentiable Stereopsis: Meshes from multiple views using differentiable rendering](https://mlsanity.com/paper/2110.05472/) (2021)
- [Convolutional Neural Opacity Radiance Fields](https://mlsanity.com/paper/2104.01772/) (2021)

## Built on by (most cited first, 16 of 16)

- [Mini-Splatting: Representing Scenes with a Constrained Number of Gaussians](https://mlsanity.com/paper/2403.14166/) (2024)
- [SRGS: Super-Resolution 3D Gaussian Splatting](https://mlsanity.com/paper/2404.10318/) (2024)
- [UW-GS: Distractor-Aware 3D Gaussian Splatting for Enhanced Underwater Scene Reconstruction](https://mlsanity.com/paper/2410.01517/) (2024)
- [Hash3D: Training-free Acceleration for 3D Generation](https://mlsanity.com/paper/2404.06091/) (2024)
- [AlignMiF: Geometry-Aligned Multimodal Implicit Field for LiDAR-Camera Joint Synthesis](https://mlsanity.com/paper/2402.17483/) (2024)
- [Efficient Scene Modeling via Structure-Aware and Region-Prioritized 3D Gaussians](https://mlsanity.com/paper/2411.12788/) (2024)
- [Neural Radiance Field-based Visual Rendering: A Comprehensive Review](https://mlsanity.com/paper/2404.00714/) (2024)
- [Neural Pruning for 3D Scene Reconstruction: Efficient NeRF Acceleration](https://mlsanity.com/paper/2504.00950/) (2025)
- [SPC-NeRF: Spatial Predictive Compression for Voxel Based Radiance Field](https://mlsanity.com/paper/2402.16366/) (2024)
- [Spatially-Adaptive Hash Encodings For Neural Surface Reconstruction](https://mlsanity.com/paper/2412.05179/) (2024)
- [NGP-RT: Fusing Multi-Level Hash Features with Lightweight Attention for Real-Time Novel View Synthesis](https://mlsanity.com/paper/2407.10482/) (2024)
- [A Convex-optimization-based Layer-wise Post-training Pruner for Large Language Models](https://mlsanity.com/paper/2408.03728/) (2024)
- [IE-SRGS: An Internal-External Knowledge Fusion Framework for High-Fidelity 3D Gaussian Splatting Super-Resolution](https://mlsanity.com/paper/2511.22233/) (2025)
- [Squeeze3D: Extreme Neural Compression with Latent Space Bridging](https://mlsanity.com/paper/2506.07932/) (2025)
- [Adaptive Time-step Training for Enhancing Spike-Based Neural Radiance Fields](https://mlsanity.com/paper/2507.23033/) (2025)
- [Camera-Agnostic Pruning of 3D Gaussian Splats via Descriptor-Based Beta Evidence](https://mlsanity.com/paper/2603.21933/) (2026)

## Abstract (arXiv)

Neural radiance fields (NeRF) have garnered significant attention, with recent works such as Instant-NGP accelerating NeRF training and evaluation through a combination of hashgrid-based positional encoding and neural networks. However, effectively leveraging the spatial sparsity of 3D scenes remains a challenge. To cull away unnecessary regions of the feature grid, existing solutions rely on prior knowledge of object shape or periodically estimate object shape during training by repeated model evaluations, which are costly and wasteful. To address this issue, we propose HollowNeRF, a novel compression solution for hashgrid-based NeRF which automatically sparsifies the feature grid during the training phase. Instead of directly compressing dense features, HollowNeRF trains a coarse 3D saliency mask that guides efficient feature pruning, and employs an alternating direction method of multipliers (ADMM) pruner to sparsify the 3D saliency mask during training. By exploiting the sparsity in the 3D scene to redistribute hash collisions, HollowNeRF improves rendering quality while using a fraction of the parameters of comparable state-of-the-art solutions, leading to a better cost-accuracy trade-off. Our method delivers comparable rendering quality to Instant-NGP, while utilizing just 31% of the parameters. In addition, our solution can achieve a PSNR accuracy gain of up to 1dB using only 56% of the parameters.