RelayGS improves dynamic 3D Gaussian reconstruction of large-scale motions by decoupling foreground from background with a learnable mask and decomposing trajectories into per-segment Relay Gaussians, gaining about 1 dB PSNR over prior art.
Hexplane: A fast representation for dynamic scenes
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
RelayGS: Reconstructing Dynamic Scenes with Large-Scale and Complex Motions via Relay Gaussians
RelayGS improves dynamic 3D Gaussian reconstruction of large-scale motions by decoupling foreground from background with a learnable mask and decomposing trajectories into per-segment Relay Gaussians, gaining about 1 dB PSNR over prior art.