3 papers
cs.CV2026
Spectral Gradient Orthogonalization Improves Differentially Private Training at Scale
Sabari Shanmugam, Nick Barnes, Kerry Taylor
Differentially private training adds isotropic Gaussian noise to clipped gradients, corrupting every singular direction equally. In vision models, where spatial correlation concent…
cs.CV2026
NumGrad-Pull: Numerical Gradient Guided Tri-plane Representation for Surface Reconstruction from Point Clouds
Ruikai Cui, Binzhu Xie, Shi Qiu +3
Reconstructing continuous surfaces from unoriented and unordered 3D points is a fundamental challenge in computer vision and graphics. Recent advancements address this problem by t…
cs.CV2026
NoiseSDF2NoiseSDF: Learning Clean Neural Fields from Noisy Supervision
Tengkai Wang, Weihao Li, Ruikai Cui +2
Reconstructing accurate implicit surface representations from point clouds remains a challenging task, particularly when data is captured using low-quality scanning devices. These…