A saliency-guided superpixel merging pipeline compresses feed-forward 3D Gaussian splatting outputs to about 5% of their primitives while largely preserving PSNR and SSIM.
Learning Efficient Fuse-and-Refine for Feed-Forward 3D Gaussian Splatting
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Compact Feed-Forward 3D Gaussians via Saliency-Guided Primitive Merging
A saliency-guided superpixel merging pipeline compresses feed-forward 3D Gaussian splatting outputs to about 5% of their primitives while largely preserving PSNR and SSIM.