QUEEN compresses per-frame Gaussian residuals with learned quantization and gating, reaching about 0.7 MB per frame, under 5 seconds of training, and 350 FPS rendering on dynamic scenes.
Videorf: Rendering dynamic radiance fields as 2d feature video streams, 2023
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 1years
2024 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
QUEEN: QUantized Efficient ENcoding of Dynamic Gaussians for Streaming Free-viewpoint Videos
QUEEN compresses per-frame Gaussian residuals with learned quantization and gating, reaching about 0.7 MB per frame, under 5 seconds of training, and 350 FPS rendering on dynamic scenes.