Assistant Professor, Stanford University
2 papers at NeurIPS 2025
Rectified Point Flow is a single generative model that turns unaligned point clouds into assembled shapes—unifying pairwise registration and multi-part assembly—and sets new state-of-the-art results across five benchmarks.
A training-free method that steers pre-trained generative rectified flow with differentiable guidance for robust, geometry-aware 3D appearance transfer across shapes and modalities.
