Track papers across labs, topics, and trends.
Search papers, labs, and topics across Lattice.
This paper introduces CC-4DGS, a novel framework for dynamic 4D Gaussian Splatting that significantly reduces storage requirements while maintaining high-quality view synthesis. By employing a computational deformation field (CDF) and a compression pipeline for canonical point-cloud attributes, the method achieves a dramatic reduction in storage size to 20-30 MB per scene, down from tens to hundreds of megabytes. Experimental results show that CC-4DGS matches the reconstruction accuracy of leading methods like Swift4D, while offering superior storage efficiency and runtime-memory performance.
Achieving 3-5× point-cloud reduction with negligible quality loss, CC-4DGS redefines the storage landscape for dynamic 4D Gaussian Splatting.
Dynamic four-dimensional (4D) Gaussian Splatting has emerged as a powerful explicit representation for highquality view synthesis, yet existing methods still require tens to hundreds of megabytes per scene due to their heavy reliance on large multi-resolution hash tables and high-dimensional Gaussian attributes. This paper presents CC-4DGS, a storage-efficient and scalable framework that rethinks both deformation modeling and canonical attribute storage. First, we introduce a computational deformation field (CDF) that replaces large multi-resolution learnable hash tables with deterministic dense hash encoding and compact neural decoders, enabling on-the-fly synthesis of deformation features while reducing deformation storage to only 1-3 MB per scene. Second, we propose a compression of canonical point-cloud attributes (CCA) pipeline that compresses highdimensional spherical harmonic appearance terms and auxiliary Gaussian attributes via conditional autoencoding, selective quantization, and residual codebooks, achieving 3-5× point-cloud reduction with negligible quality loss. Together, these components yield a unified representation that preserves real-time rendering performance while reducing total storage to 20-30 MB. Extensive experiments across the N3DV and Technicolor Light Field datasets demonstrate that CC-4DGS achieves reconstruction accuracy comparable to state-of-the-art methods such as Swift4D, while offering significantly improved storage efficiency and favorable runtime-memory trade-offs.