Papers
1–3 of 3Research Paper·Mar 17, 2026
NanoGS: Training-Free Gaussian Splat Simplification
3D Gaussian Splat (3DGS) enables high-fidelity, real-time novel view synthesis by representing scenes with large sets of anisotropic primitives, but often requires millions of Splats, incurring signif...
7.0 viability
Research Paper·Mar 17, 2026
ProgressiveAvatars: Progressive Animatable 3D Gaussian Avatars
In practical real-time XR and telepresence applications, network and computing resources fluctuate frequently. Therefore, a progressive 3D representation is needed. To this end, we propose Progressive...
4.0 viability
Research Paper·Mar 9, 2026
SkipGS: Post-Densification Backward Skipping for Efficient 3DGS Training
3D Gaussian Splatting (3DGS) achieves real-time novel-view synthesis by optimizing millions of anisotropic Gaussians, yet its training remains expensive, with the backward pass dominating runtime in t...
3.0 viability