GETA-3DGS is the first automatic joint structured pruning and quantization framework for 3D Gaussian Splatting, achieving roughly 5x storage reduction on standard datasets without per-scene thresholds.
gsplat: An open-source library for gaussian splatting.ArXiv, abs/2409.06765
6 Pith papers cite this work. Polarity classification is still indexing.
6
Pith papers citing it
representative citing papers
Bit flips in 3D Gaussian splatting are highly concentrated in effect with certain high-order bits corrupting up to 75.7% of the frame, but a support guard reduces the worst footprint to 11.68% while preserving clean performance and improving quality under accumulated faults.
An end-to-end transcoding pipeline creates 3D Gaussian splatting models from plenoptic point clouds or meshes without original multi-view images, using custom initialization and surface constraints for high-quality output with fewer splats and faster convergence.
Dense initialization of 3DGS does not consistently beat sparse SfM initialization for standard novel views, but improves off-trajectory generalization; no densification method wins everywhere.
Proposes a physics-based 3D Gaussian framework that disentangles appearance from medium effects for high-quality underwater novel view synthesis and scene restoration.
Turbo-GS accelerates 3D Gaussian Splatting training via dilated rendering of pixel subsets, convergence-aware Gaussian budget allocation, and combined positional-appearance error densification to enable faster 4K fitting with preserved or improved rendering quality.
citing papers explorer
-
GETA-3DGS: Automatic Joint Structured Pruning and Quantization for 3D Gaussian Splatting
GETA-3DGS is the first automatic joint structured pruning and quantization framework for 3D Gaussian Splatting, achieving roughly 5x storage reduction on standard datasets without per-scene thresholds.
-
Single-Event Upsets in 3D Gaussian Splatting Rendering: Bit-Level Criticality, Spatial Extent, and a Parallel Support Guard
Bit flips in 3D Gaussian splatting are highly concentrated in effect with certain high-order bits corrupting up to 75.7% of the frame, but a support guard reduces the worst footprint to 11.68% while preserving clean performance and improving quality under accumulated faults.
-
Transcoding a 3D Gaussian Splatting Model from a Plenoptic Point Cloud or Mesh without the Original Multi-view Images
An end-to-end transcoding pipeline creates 3D Gaussian splatting models from plenoptic point clouds or meshes without original multi-view images, using custom initialization and surface constraints for high-quality output with fewer splats and faster convergence.
-
The Role of Initialization in 3D Gaussian Splatting
Dense initialization of 3DGS does not consistently beat sparse SfM initialization for standard novel views, but improves off-trajectory generalization; no densification method wins everywhere.
-
3D-UIR: 3D Gaussian for Underwater 3D Scene Reconstruction via Physics Based Appearance-Medium Decoupling
Proposes a physics-based 3D Gaussian framework that disentangles appearance from medium effects for high-quality underwater novel view synthesis and scene restoration.
-
Turbo-GS: Accelerating 3D Gaussian Fitting for High-Quality Radiance Fields
Turbo-GS accelerates 3D Gaussian Splatting training via dilated rendering of pixel subsets, convergence-aware Gaussian budget allocation, and combined positional-appearance error densification to enable faster 4K fitting with preserved or improved rendering quality.