arXiv Computer Vision
CleanGS: Pareto-Guided Post-Hoc Cleanup of 3D Gaussian Splatting Scenes
Read the original on arXiv Computer Vision →The Flow has not summarised this story yet — read it at arXiv Computer Vision.
Related stories
arXiv Computer Vision
Sep 28
Gauss What You Need: Compact Gaussian Splatting Across Scene Scales
Gauss What You Need: Compact Gaussian Splatting Across Scene Scales introduces TangoGS, a method that automatically selects the number of Gaussian primitives for 3D Gaussian Splatting by combining capture-derived model sizing with training-based adaptation. The approach first estimates a learning allowance based on the capture’s total pixels, then adjusts the number of Gaussians during training according to reconstruction quality. On standard benchmarks, TangoGS matches the best baseline’s PSNR while using 48% fewer Gaussians, and on larger captures it scales automatically to achieve the highest mean PSNR with 2.3× more Gaussians.
arXiv Computer Vision
Oct 7
DensiTok: Making Feed-Forward 3D Gaussian Splatting See More Views Than It Is Given
arXiv:2610.07958v1 Announce Type: new Abstract: Feed-forward 3D Gaussian Splatting (3DGS) reconstructs a scene in a single forward pass, replacing per-scene optimization with a network trained across...
arXiv Machine Learning
Jul 7
Provable Pruning for Efficient 3D Gaussian Splatting via Coresets
arXiv:2607. 02721v1 Announce Type: cross Abstract: 3D Gaussian Splatting (3DGS) enables high-quality real-time novel-view synthesis, but practical scenes often contain millions of Gaussians, making compression essential for deployment on limited hardware.
arXiv Computer Vision
1d ago
ParetoGS: High-Quality Continuous-Budget 3D Gaussian Splatting with Sparse Adapted Anchors
arXiv:2610.34235v1 Announce Type: new Abstract: Scalable 3D Gaussian Splatting allows one scene representation to serve different Gaussian-count budgets, yet its quality-budget curve may lag behind m...
arXiv Computer Vision
1d ago
Birth-Death Structural Learning for 3D Gaussian Splatting
arXiv:2610.34344v1 Announce Type: new Abstract: 3D Gaussian Splatting (3DGS) has become a standard representation for real-time novel-view synthesis. Yet, its quality-efficiency trade-off still relie...
arXiv AI
Jul 8
Rendering-Aware Bayesian 3D Gaussian Splatting with Native Uncertainty and Adaptive Complexity Control
arXiv:2607. 05522v1 Announce Type: cross Abstract: 3D Gaussian splatting (3DGS) is a strong representation for real-time novel-view synthesis, but its standard training pipeline relies on point estimates and hand-tuned heuristics, providing no native uncertainty or principled complexity control.