Search papers, labs, and topics across Lattice.
The authors present an estimator-agnostic compression framework for dynamic 3D Gaussian Splatting (3DGS) that transforms temporal redundancy into spatial redundancy by concatenating temporal Gaussian groups, augmenting them with frame indices, and applying off-the-shelf static 3DGS codecs. This decoupled approach removes dependencies on specialized motion vectors or specific upstream training architectures while maintaining robustness across both tracked and untracked Gaussian sequences. Across six N3DV benchmarks, the method achieves -42.0% to -71.8% BD-rate improvements on tracked sets over per-frame coding and cuts BD-rate by 46.2% when integrated into standard I/P-frame codecs.
Dynamic 3D scene compression does not require specialized motion models鈥攕imply appending frame indices to Gaussians and feeding them into off-the-shelf static codecs slashes bitrates by up to 71.8%.
Dynamic 3D Gaussian splats (3DGS) model time-varying scenes using a separate Gaussian set per frame. While neighboring video frames are highly correlated due to smooth motion, Gaussian representations retain this correlation to varying degrees, depending on whether the estimator tracks them across time. Some 3DGS compression methods integrate the estimation to exploit temporal redundancy; here, we focus on robust compression regardless of the estimator. We concatenate groups of frames into one Gaussian set, augment each Gaussian with a frame index, and pass it to a static (i.e., non-temporal) 3DGS codec, converting temporal redundancy into spatial redundancy. Concatenated sets are spatially partitioned to limit memory. Our technique requires neither a motion model nor knowledge of the training method. Averaged over six N3DV sequences, all six static codecs achieve gains on tracked sets (-42.0% to -71.8% BD-rate) over per-frame coding. On untracked sets, all codecs except HGSC, which appears incompatible with our technique, remain competitive with per-frame coding (-3.5% to +5.0%). We further replace D-FCGS's I-frame coding with our technique while retaining its P-frame coding, yielding an overall BD-rate of -46.2%. We propose to visualize"trackedness"using an inter-frame similarity metric. The project is available at https://wcjj1236.github.io/d3dgs-benchmark.
