Search Results for author:
Found 4 papers, 0 papers with code
Self-recovery of memory via generative replay
We demonstrate this capacity of the architecture across several continual learning tasks and environments.
Multi-View Photometric Stereo: A Robust Solution and Benchmark Dataset for Spatially Varying Isotropic Materials
From a single viewpoint, we use a set of photometric stereo images to identify surface points with the same distance to the camera.
Humans can decipher adversarial images
This seemingly extreme divergence between human and machine classification challenges the promise of these new advances, both as applied image-recognition systems and also as models of the human mind.
Multi-view Photometric Stereo with Spatially Varying Isotropic Materials
We present a method to capture both 3D shape and spatially varying reflectance with a multi-view photometric stereo technique that works for general isotropic materials.
