Search papers, labs, and topics across Lattice.
M distractors dataset [46]. It is trained using the AdamW [39] optimizer in PyTorch [44] with an NVIDIA 2080 Ti GPU. The detector head is trained using 400k samples center cropped at
NVIDIA Research1
0
3
Forget complex architectures: RaCo achieves SOTA keypoint matching and repeatability by cleverly combining ranking and covariance estimation in a lightweight network, trained without covisible image pairs.
