# Deep Implicit Volume Compression

arXiv: https://arxiv.org/abs/2005.08877 · HTML: https://mlsanity.com/paper/2005.08877/

## Key facts

- Cited by 26 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 18 May 2020.

## Built on by (most cited first, 26 of 26)

- [iMAP: Implicit Mapping and Positioning in Real-Time](https://mlsanity.com/paper/2103.12352/) (2021)
- [Neural Geometric Level of Detail: Real-time Rendering with Implicit 3D Shapes](https://mlsanity.com/paper/2101.10994/) (2021)
- [Variable Bitrate Neural Fields](https://mlsanity.com/paper/2206.07707/) (2022)
- [An Introduction to Neural Data Compression](https://mlsanity.com/paper/2202.06533/) (2022)
- [Density-preserving Deep Point Cloud Compression](https://mlsanity.com/paper/2204.12684/) (2022)
- [Multiresolution Deep Implicit Functions for 3D Shape Representation](https://mlsanity.com/paper/2109.05591/) (2021)
- [HUMAN4D: A Human-Centric Multimodal Dataset for Motions and Immersive Media](https://mlsanity.com/paper/2110.07235/) (2021)
- [NeuralVDB: High-resolution Sparse Volume Representation using Hierarchical Neural Networks](https://mlsanity.com/paper/2208.04448/) (2022)
- [LVAC: Learned Volumetric Attribute Compression for Point Clouds using Coordinate Based Networks](https://mlsanity.com/paper/2111.08988/) (2021)
- [Compact Neural Graphics Primitives with Learned Hash Probing](https://mlsanity.com/paper/2312.17241/) (2023)
- [PRIF: Primary Ray-based Implicit Function](https://mlsanity.com/paper/2208.06143/) (2022)
- [VertexRegen: Mesh Generation with Continuous Level of Detail](https://mlsanity.com/paper/2508.09062/) (2025)
- [3D Shapes Local Geometry Codes Learning with SDF](https://mlsanity.com/paper/2108.08593/) (2021)
- [Volumetric Attribute Compression for 3D Point Clouds using Feedforward Network with Geometric Attention](https://mlsanity.com/paper/2304.00335/) (2023)
- [Lagrangian Hashing for Compressed Neural Field Representations](https://mlsanity.com/paper/2409.05334/) (2024)
- [F-Hash: Feature-Based Hash Design for Time-Varying Volume Visualization via Multi-Resolution Tesseract Encoding](https://mlsanity.com/paper/2507.03836/) (2025)
- [Generalizable Pose Estimation Using Implicit Scene Representations](https://mlsanity.com/paper/2305.17252/) (2023)
- [Learned Nonlinear Predictor for Critically Sampled 3D Point Cloud Attribute Compression](https://mlsanity.com/paper/2311.13539/) (2023)
- [SLAIM: Robust Dense Neural SLAM for Online Tracking and Mapping](https://mlsanity.com/paper/2404.11419/) (2024)
- [Plenoptic PNG: Real-Time Neural Radiance Fields in 150 KB](https://mlsanity.com/paper/2409.15689/) (2024)
- [Deep Unrolling of Sparsity-Induced RDO for 3D Point Cloud Attribute Coding](https://mlsanity.com/paper/2509.08685/) (2025)
- [A deep perceptual metric for 3D point clouds](https://mlsanity.com/paper/2102.12839/) (2021)
- [DeepCompress: Efficient Point Cloud Geometry Compression](https://mlsanity.com/paper/2106.01504/) (2021)
- [A Comparison of Tiny-nerf versus Spatial Representations for 3d Reconstruction](https://mlsanity.com/paper/2301.11522/) (2023)
- [A Novel Implicit Neural Representation for Volume Data](https://mlsanity.com/paper/2403.08566/) (2024)
- [Hierarchical Frequency-Domain Compression of Implicit Geometric Representations for Large-Scale Point Clouds](https://mlsanity.com/paper/2609.32789/) (2026)

## Abstract (arXiv)

We describe a novel approach for compressing truncated signed distance fields (TSDF) stored in 3D voxel grids, and their corresponding textures. To compress the TSDF, our method relies on a block-based neural network architecture trained end-to-end, achieving state-of-the-art rate-distortion trade-off. To prevent topological errors, we losslessly compress the signs of the TSDF, which also upper bounds the reconstruction error by the voxel size. To compress the corresponding texture, we designed a fast block-based UV parameterization, generating coherent texture maps that can be effectively compressed using existing video compression algorithms. We demonstrate the performance of our algorithms on two 4D performance capture datasets, reducing bitrate by 66% for the same distortion, or alternatively reducing the distortion by 50% for the same bitrate, compared to the state-of-the-art.