Search papers, labs, and topics across Lattice.
6 papers from Berkeley AI Research (BAIR) on Computer Vision
Adversarial clothing with non-overlapping visible-thermal patterns can reliably evade RGB-T detectors, even transferring across different fusion architectures.
Unlock zero-shot generalization in robot manipulation by generating diverse, affordance-aware training data with 3D generative models and Vision Foundation Models.
Unlock 36% better video depth estimation and 20% better camera pose estimation by simply letting your model learn from its own unlabeled video predictions.
Get 3x the imitation learning performance from your robot with just a few extra cameras.
Unlock autonomous driving with YouTube: a new label-free pretraining method learns driving representations directly from unposed in-the-wild videos, outperforming LiDAR baselines with only a single monocular camera.
Denoising diffusion models can significantly outperform discriminative methods in learning-to-rank, suggesting a new path for improving information retrieval.
