AI RESEARCH
SpectralSplats: Robust Differentiable Tracking via Spectral Moment Supervision
arXiv CS.CV
•
ArXi:2603.24036v1 Announce Type: new 3D Gaussian Splatting (3DGS) enables real-time, photorealistic novel view synthesis, making it a highly attractive representation for model-based video tracking. However, leveraging the differentiability of the 3DGS renderer "in the wild" remains notoriously fragile. A fundamental bottleneck lies in the compact, local of the Gaussian primitives.