Global-Aware Registration of Less-Overlap RGB-D Scans

Sun, Che; Jia, Yunde; Guo, Yi; Wu, Yuwei

doi:10.1109/cvpr52688.2022.00625

Cited by 3 publications

(1 citation statement)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Similarly, Shakil [45] showed that two (or more) nonoverlapping videos recorded by uncalibrated video cameras can be aligned using the temporal changes and frame-to-frame motion within the sequences. The registration of nonoverlapping RGB-D scans [46,21] is a common extension of the image-only problem, where a global representation of a scene is often estimated.…”

Section: Related Workmentioning

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

Section: Related Workmentioning

confidence: 99%

Estimating Extreme 3D Image Rotation with Transformer Cross-Attention

Dekel¹,

Keller²

2023

Preprint

View full text Add to dashboard Cite

show abstract

Deep Image Registration With Depth-Aware Homography Estimation

Huang

Pan

Cheng

et al. 2023

IEEE Signal Process. Lett.

View full text Add to dashboard Cite

Review on Deep Learning Algorithms and Benchmark Datasets for Pairwise Global Point Cloud Registration

Zhao

Fan

2023

Remote Sensing

View full text Add to dashboard Cite

Point cloud registration is the process of aligning point clouds collected at different locations of the same scene, which transforms the data into a common coordinate system and forms an integrated dataset. It is a fundamental task before the application of point cloud data. Recent years have witnessed the rapid development of various deep-learning-based global registration methods to improve performance. Therefore, it is appropriate to carry out a comprehensive review of the more recent developments in this area. As the developments require access to large benchmark point cloud datasets, the most widely used public datasets are also reviewed. The performance of deep-learning-based registration methods on the benchmark datasets are summarized using the reported performance metrics in the literature. This forms part of a critical discussion of the strengths and weaknesses of the various methods considered in this article, which supports presentation of the main challenges currently faced in typical global point cloud registration tasks that use deep learning methods. Recommendations for potential future studies on this topic are provided.

show abstract

Global-Aware Registration of Less-Overlap RGB-D Scans

Cited by 3 publications

References 20 publications

Estimating Extreme 3D Image Rotation with Transformer Cross-Attention

Estimating Extreme 3D Image Rotation with Transformer Cross-Attention

Deep Image Registration With Depth-Aware Homography Estimation

Review on Deep Learning Algorithms and Benchmark Datasets for Pairwise Global Point Cloud Registration

Contact Info

Product

Resources

About