Estimating Extreme 3D Image Rotation with Transformer Cross-Attention

arXiv:2303.02615v2 Announce Type: replace
Abstract: The estimation of large and extreme image rotation plays a key role in multiple computer vision domains, where the rotated images are related by a limited or a non-overlapping field of view. Contemporary approaches apply convolutional neural networks to compute a 4D correlation volume to estimate the relative rotation between image pairs. In this work, we propose a cross-attention-based approach that utilizes CNN feature maps and a Transformer-Encoder, to compute the cross-attention between the activation …

abstract apply arxiv attention compute computer computer vision convolutional neural networks correlation cs.cv domains image images key multiple networks neural networks role rotation transformer type view vision