Postdoc, Griffith University
2 papers at NeurIPS 2025
We propose graph consistency regularization, a method that improves classification by aligning feature and prediction structures to suppress inter-class noise and strengthen intra-class cohesion.
We propose Puzzles, a controllable augmentation that simulates high-quality posed video-depth data from a single image or clip, boosting 3D reconstruction performance with much less training data.
