Deep Implicit Volume Compression
This work addresses efficient compression for 3D performance capture data, which is incremental as it builds on existing TSDF and texture compression techniques.
The paper tackles the problem of compressing truncated signed distance fields (TSDF) and textures in 3D voxel grids, achieving a 66% bitrate reduction for the same distortion or a 50% distortion reduction for the same bitrate compared to state-of-the-art methods.
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.