🏢 Monash University

Normal-GS improves 3D Gaussian Splatting by integrating normal vectors into the rendering pipeline, achieving near state-of-the-art visual quality with accurate surface normals in real-time.

MVSplat360: Generating stunning 360° views from just a few images!

FasMe: a novel meta-learning approach delivers fast and sample-efficient precision matrix estimation, surpassing existing methods in accuracy and speed for small sample datasets.

Eigen-SAM significantly boosts generalization in deep learning by directly addressing SAM’s limitations through explicit top Hessian eigenvalue regularization.

This research introduces adversarial concept preservation, a novel method for safely erasing undesirable concepts from diffusion models, outperforming existing techniques by preserving related sensiti…