Research topics
Related publications and engineering projects
Presents LNR, a coarse-to-fine robust multi-model fitting framework that screens minimal sample sets and refines hypothesis neighborhoods to overcome combinatorial explosion under multi-structure overlap.
Read paper story
Proposes a geometry-conditioned diffusion paradigm for sample consensus, iteratively refining candidate minimal sets to achieve robust estimation under extreme outlier ratios.
Read paper story
Reinforcement-learning-guided hypothesis sampling for consensus-based robust estimation under extreme outlier ratios.
Read paper story