# Neural Pruning for 3D Scene Reconstruction: Efficient NeRF Acceleration

arXiv: https://arxiv.org/abs/2504.00950 · HTML: https://mlsanity.com/paper/2504.00950/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Builds on 15 of its 27 references that are in the map.
- First posted on arXiv 1 Apr 2025.

## Builds on (most cited first, 15 of 15)

- [Putting NeRF on a Diet: Semantically Consistent Few-Shot View Synthesis](https://mlsanity.com/paper/2104.00677/) (2021)
- [Editing Conditional Radiance Fields](https://mlsanity.com/paper/2105.06466/) (2021)
- [Compressible-composable NeRF via Rank-residual Decomposition](https://mlsanity.com/paper/2205.14870/) (2022)
- [Object-Centric Neural Scene Rendering](https://mlsanity.com/paper/2012.08503/) (2020)
- [VMT-Adapter: Parameter-Efficient Transfer Learning for Multi-Task Dense Scene Understanding](https://mlsanity.com/paper/2312.08733/) (2023)
- [MmAP : Multi-modal Alignment Prompt for Cross-domain Multi-task Learning](https://mlsanity.com/paper/2312.08636/) (2023)
- [Data-Independent Neural Pruning via Coresets](https://mlsanity.com/paper/1907.04018/) (2019)
- [NeRF in detail: Learning to sample for view synthesis](https://mlsanity.com/paper/2106.05264/) (2021)
- [Coreset-Based Neural Network Compression](https://mlsanity.com/paper/1807.09810/) (2018)
- [NeuSample: Neural Sample Field for Efficient View Synthesis](https://mlsanity.com/paper/2111.15552/) (2021)
- [Data-Independent Structured Pruning of Neural Networks via Coresets](https://mlsanity.com/paper/2008.08316/) (2020)
- [HollowNeRF: Pruning Hashgrid-Based NeRFs with Trainable Collision Mitigation](https://mlsanity.com/paper/2308.10122/) (2023)
- [CausalSR: Structural Causal Model-Driven Super-Resolution with Counterfactual Inference](https://mlsanity.com/paper/2501.15852/) (2025)
- [Neural 3D Scene Compression via Model Compression](https://mlsanity.com/paper/2105.03120/) (2021)
- [Research and Design on Intelligent Recognition of Unordered Targets for Robots Based on Reinforcement Learning](https://mlsanity.com/paper/2503.07340/) (2025)

## Built on by (most cited first, 10 of 10)

- [JanusVLN: Decoupling Semantics and Spatiality with Dual Implicit Memory for Vision-Language Navigation](https://mlsanity.com/paper/2509.22548/) (2025)
- [Think with 3D: Geometric Imagination Grounded Spatial Reasoning from Limited Views](https://mlsanity.com/paper/2510.18632/) (2025)
- [SwiftVLA: Unlocking Spatiotemporal Dynamics for Lightweight VLA Models at Minimal Overhead](https://mlsanity.com/paper/2512.00903/) (2025)
- [VAG: Dual-Stream Video-Action Generation for Embodied Data Synthesis](https://mlsanity.com/paper/2604.09330/) (2026)
- [Instruction Tuning and CoT Prompting for Contextual Medical QA with LLMs](https://mlsanity.com/paper/2506.12182/) (2025)
- [Automated Parking Trajectory Generation Using Deep Reinforcement Learning](https://mlsanity.com/paper/2504.21071/) (2025)
- [Coverage-Aware Web Crawling for Domain-Specific Supplier Discovery via a Web--Knowledge--Web Pipeline](https://mlsanity.com/paper/2602.24262/) (2026)
- [A Machine Learning-Based Study on the Synergistic Optimization of Supply Chain Management and Financial Supply Chains from an Economic Perspective](https://mlsanity.com/paper/2509.03673/) (2025)
- [Modality-Aware Infrared and Visible Image Fusion with Target-Aware Supervision](https://mlsanity.com/paper/2509.11476/) (2025)
- [Gromov-Wasserstein Quantization and Clustering: Structure, Rates, and Algorithms](https://mlsanity.com/paper/2608.11016/) (2026)

## Abstract (arXiv)

Neural Radiance Fields (NeRF) have become a popular 3D reconstruction approach in recent years. While they produce high-quality results, they also demand lengthy training times, often spanning days. This paper studies neural pruning as a strategy to address these concerns. We compare pruning approaches, including uniform sampling, importance-based methods, and coreset-based techniques, to reduce the model size and speed up training. Our findings show that coreset-driven pruning can achieve a 50% reduction in model size and a 35% speedup in training, with only a slight decrease in accuracy. These results suggest that pruning can be an effective method for improving the efficiency of NeRF models in resource-limited settings.