Merge branch 'main' of github.com:w-m/3dgs-compression-survey

w-m · Sep 18, 2024 · 8d5e547 · 8d5e547
2 parents cfeca4e + c8693a4
commit 8d5e547
Show file tree

Hide file tree

Showing 2 changed files with 4 additions and 0 deletions.
diff --git a/methods/fang2024minisplatting.md b/methods/fang2024minisplatting.md
@@ -0,0 +1,2 @@
+### Mini-Splatting: Representing Scenes with a Constrained Number of Gaussians
+Mini-Splatting enhances Gaussian distribution through Blur Split, which refines Gaussians in blurred regions, and Depth Reinitialization, which repositions Gaussians based on newly generated depth points, calculated from the mid-point of ray intersections with Gaussian ellipsoids, thus avoiding artifacts from alpha blending. For simplification, Intersection Preserving retains Gaussians with the greatest visual impact, while Sampling maintains geometric integrity and rendering quality, reducing complexity.
diff --git a/methods/kim2024CVPR.md b/methods/kim2024CVPR.md
@@ -0,0 +1,2 @@
+### Color-cued Efficient Densification Method for 3D Gaussian Splatting
+This method introduces a simple yet effective modification to the densification process in the original 3D Gaussian Splatting (3DGS). It leverages the view-independent (0th) spherical harmonics (SH) coefficient gradient to better assess color cues for densification, while using the 2D position gradient more coarsely to refine areas where structure-from-motion (SfM) struggles to capture fine structures.
Original file line number	Diff line number	Diff line change
		@@ -0,0 +1,2 @@
		### Mini-Splatting: Representing Scenes with a Constrained Number of Gaussians
		Mini-Splatting enhances Gaussian distribution through Blur Split, which refines Gaussians in blurred regions, and Depth Reinitialization, which repositions Gaussians based on newly generated depth points, calculated from the mid-point of ray intersections with Gaussian ellipsoids, thus avoiding artifacts from alpha blending. For simplification, Intersection Preserving retains Gaussians with the greatest visual impact, while Sampling maintains geometric integrity and rendering quality, reducing complexity.
Original file line number	Diff line number	Diff line change
		@@ -0,0 +1,2 @@
		### Color-cued Efficient Densification Method for 3D Gaussian Splatting
		This method introduces a simple yet effective modification to the densification process in the original 3D Gaussian Splatting (3DGS). It leverages the view-independent (0th) spherical harmonics (SH) coefficient gradient to better assess color cues for densification, while using the 2D position gradient more coarsely to refine areas where structure-from-motion (SfM) struggles to capture fine structures.