MrNeRF (@janusch_patas)
2025-06-07 | โค๏ธ 149 | ๐ 13
Code dropped! Link in comment! https://x.com/janusch_patas/status/1931365862339973353/video/1
๋ฏธ๋์ด
์ธ์ฉ ํธ์
MrNeRF (@janusch_patas)
QUEEN: QUantized Efficient ENcoding of Dynamic Gaussians for Streaming Free-viewpoint Videos
Contributions:
โข We propose a Gaussian residual-based framework to model 3D dynamic scenes for online FVV without any structural constraints. This allows free learning of all 3D-GS attribute residuals, resulting in higher model expressiveness.
โข We introduce a learned quantization-sparsity framework for compressing per-frame residuals, initializing and training it efficiently using viewspace gradient differences that separate dynamic and static scene content.
โข On various challenging real-world dynamic scenes, we surpass existing state-of-the-art approaches on all metrics: reconstruction quality, memory utilization, and training and rendering speed.
๐ฌ ์์
