mlsanityData to 14 Oct 2026

Neural Pruning for 3D Scene Reconstruction: Efficient NeRF Acceleration

arXiv 2504.00950 ↗First posted 1 Apr 2025cs.CVcited by 10

Not on the map. Why?

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.

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

15 of 27 references.

References · 15

  1. 2021Putting NeRF on a Diet: Semantically Consistent Few-Shot View Synthesiscited by 464
  2. 2021Editing Conditional Radiance Fieldscited by 222
  3. 2022Compressible-composable NeRF via Rank-residual Decompositioncited by 92
  4. 2020Object-Centric Neural Scene Renderingcited by 90
  5. 2023VMT-Adapter: Parameter-Efficient Transfer Learning for Multi-Task Dense Scene Understandingcited by 62
  6. 2023MmAP : Multi-modal Alignment Prompt for Cross-domain Multi-task Learningcited by 41
  7. 2019Data-Independent Neural Pruning via Coresetscited by 35
  8. 2021NeRF in detail: Learning to sample for view synthesiscited by 35
  9. 2018Coreset-Based Neural Network Compressioncited by 27
  10. 2021NeuSample: Neural Sample Field for Efficient View Synthesiscited by 21
  11. 2020Data-Independent Structured Pruning of Neural Networks via Coresetscited by 17
  12. 2023HollowNeRF: Pruning Hashgrid-Based NeRFs with Trainable Collision Mitigationcited by 16
3 more
  1. 2025CausalSR: Structural Causal Model-Driven Super-Resolution with Counterfactual Inferencecited by 12
  2. 2021Neural 3D Scene Compression via Model Compressioncited by 7
  3. 2025Research and Design on Intelligent Recognition of Unordered Targets for Robots Based on Reinforcement Learningcited by 6

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 7; 2026: 3.

10 papers.

  1. 2025JanusVLN: Decoupling Semantics and Spatiality with Dual Implicit Memory for Vision-Language Navigationcited by 89
  2. 2025Think with 3D: Geometric Imagination Grounded Spatial Reasoning from Limited Viewscited by 65
  3. 2025SwiftVLA: Unlocking Spatiotemporal Dynamics for Lightweight VLA Models at Minimal Overheadcited by 26
  4. 2026VAG: Dual-Stream Video-Action Generation for Embodied Data Synthesiscited by 6
  5. 2025Instruction Tuning and CoT Prompting for Contextual Medical QA with LLMscited by 5
  6. 2025Automated Parking Trajectory Generation Using Deep Reinforcement Learningcited by 4
  7. 2026Coverage-Aware Web Crawling for Domain-Specific Supplier Discovery via a Web--Knowledge--Web Pipelinecited by 4
  8. 2025A Machine Learning-Based Study on the Synergistic Optimization of Supply Chain Management and Financial Supply Chains from an Economic Perspectivecited by 1
  9. 2025Modality-Aware Infrared and Visible Image Fusion with Target-Aware Supervisioncited by 1
  10. 2026Gromov-Wasserstein Quantization and Clustering: Structure, Rates, and Algorithmscited by 0