# Hash Grid Feature Pruning

arXiv: https://arxiv.org/abs/2512.22882 · HTML: https://mlsanity.com/paper/2512.22882/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 5 of its 7 references that are in the map.
- First posted on arXiv 28 Dec 2025.

## Builds on (most cited first, 5 of 5)

- [Instant Neural Graphics Primitives with a Multiresolution Hash Encoding](https://mlsanity.com/paper/2201.05989/) (2022)
- [HAC: Hash-grid Assisted Context for 3D Gaussian Splatting Compression](https://mlsanity.com/paper/2403.14530/) (2024)
- [3DGStream: On-the-Fly Training of 3D Gaussians for Efficient Streaming of Photo-Realistic Free-Viewpoint Videos](https://mlsanity.com/paper/2403.01444/) (2024)
- [HAC++: Towards 100X Compression of 3D Gaussian Splatting](https://mlsanity.com/paper/2501.12255/) (2025)
- [Swift4D:Adaptive divide-and-conquer Gaussian Splatting for compact and efficient reconstruction of dynamic scene](https://mlsanity.com/paper/2503.12307/) (2025)

## Built on by (most cited first, 3 of 3)

- [HPC: Hierarchical Point-based Latent Representation for Streaming Dynamic Gaussian Splatting Compression](https://mlsanity.com/paper/2602.00671/) (2026)
- [Camera-Agnostic Pruning of 3D Gaussian Splats via Descriptor-Based Beta Evidence](https://mlsanity.com/paper/2603.21933/) (2026)
- [SoLAR: Error-Resilient Streamable Long-Horizon Free-Viewpoint Video Reconstruction with Anchor Activation and Latent Recalibration](https://mlsanity.com/paper/2605.07346/) (2026)

## Abstract (arXiv)

Hash grids are widely used to learn an implicit neural field for Gaussian splatting, serving either as part of the entropy model or for inter-frame prediction. However, due to the irregular and non-uniform distribution of Gaussian splats in 3D space, numerous sparse regions exist, rendering many features in the hash grid invalid. This leads to redundant storage and transmission overhead. In this work, we propose a hash grid feature pruning method that identifies and prunes invalid features based on the coordinates of the input Gaussian splats, so that only the valid features are encoded. This approach reduces the storage size of the hash grid without compromising model performance, leading to improved rate-distortion performance. Following the Common Test Conditions (CTC) defined by the standardization committee, our method achieves an average bitrate reduction of 8% compared to the baseline approach.