This paper introduces a novel deep-learning method for efficiently compressing truncated signed distance function (TSDF) volumes. Previous works divide TSDF volumes into blocks and encode each block into the same number of latent codes, regardless of the geometric complexity stored in each block. This results in higher bitrates and increased complexity in arithmetic coding, as both complex and simple geometric blocks require the same number of latent codes. To address these inefficiencies, we propose a hyperprior-based compression model with latent code selection (HyperLCS) that dynamically adjusts the number of latent codes based on the geometric complexity of TSDF blocks. Through geometry-complexity-adaptive selective coding, HyperLCS reduces unnecessary bit allocation and arithmetic coding complexity, leading to improved coding efficiency, lower bitrates, and faster compression times. Furthermore, we introduce the Sampling-Enhancing Residual Block (SERB), a modified residual block designed to compensate for feature loss during spatial sampling by calculating residuals at the input resolution and adjusting the sampled output. Experimentally, SERB demonstrated improved TSDF volume compression performance compared to conventional residual blocks with the same capacity in terms of weight parameters. By combining HyperLCS and SERB, our method achieves superior TSDF volume compression performance, maintaining high data fidelity even at high compression rates. Experimental results demonstrate substantial improvements over existing techniques.
Kim et al. (Sat,) studied this question.