A Reliable Online Method for Joint Estimation of Focal Length and Camera Rotation

Qian, Yiming; Elder, James H.

doi:10.1007/978-3-031-19769-7_15

Cited by 4 publications

(1 citation statement)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…1 relates to the seminal work by Coughlan and Yuille [10] who introduced a technique that is premised on linear structures within an image, arising primarily from three directions that are mutually orthogonal, one vertical (building walls), and two horizontal (ground-level pavements, roads, etc.). Similarly, the "Single View Metrology" by Criminisi et al [11] and its extensions [59,25,40], use parallel lines in the image and their corresponding vanishing points [20] for camera calibration. Moreover, the relative rotation of a camera can also be estimated using illumination cues [2], by analyzing the directions of the lighting and cast shadows.…”

Section: Introductionmentioning

confidence: 99%

Estimating Extreme 3D Image Rotation with Transformer Cross-Attention

Dekel¹,

Keller²

2023

Preprint

View full text Add to dashboard Cite

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 nonoverlapping 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-attentionbased approach that utilizes CNN feature maps and a Transformer-Encoder, to compute the cross-attention between the activation maps of the image pairs, which is shown to be an improved equivalent of the 4D correlation volume, used in previous works. In the suggested approach, higher attention scores are associated with image regions that encode visual cues of rotation. Our approach is end-to-end trainable and optimizes a simple regression loss. It is experimentally shown to outperform contemporary state-of-the-art schemes when applied to commonly used image rotation datasets and benchmarks, and establishes a new state-of-the-art accuracy on these datasets. We make our code publicly available 1 .

show abstract