Estimating Extreme 3D Image Rotations using Cascaded Attention
Estimating large extreme inter-image rotations is critical for numerous computer vision domains involving images related by limited or non-overlapping fields of view. In this work we propose an attention-based approach with a pipeline of novel algorithmic components. First as rotation estimation pertains to image pairs we introduce an inter-image distillation scheme using Decoders to improve embeddings. Second whereas contemporary methods compute a 4D correlation volume (4DCV) encoding inter-image relationships we propose an Encoder-based cross-attention approach between activation maps to compute an enhanced equivalent of the 4DCV. Finally we present a cascaded Decoder-based technique for alternately refining the cross-attention and the rotation query. Our approach outperforms current state-of-the-art methods on extreme rotation estimation. We make our code publicly available.
Code (0)
등록된 구현이 없습니다.
Tasks
DecoderSimilar Papers 제목 키워드 기반
Extreme Rotation Estimation in the Wild
We present a technique and benchmark dataset for estimating the relative 3D orientation between a pair of Internet images captured in an extreme setting, where the images have limited or non-overlapping field of views. P…
3D ReconstructionExtreme Rotation Estimation using Dense Correlation Volumes
We present a technique for estimating the relative 3D rotation of an RGB image pair in an extreme setting, where the images have little or no overlap. We observe that, even when images do not overlap, there may be rich h…
Feature CorrelationCNN-based Cascaded Multi-task Learning of High-level Prior and Density Estimation for Crowd Counting
Estimating crowd count in densely crowded scenes is an extremely challenging task due to non-uniform scale variations. In this paper, we propose a novel end-to-end cascaded network of CNNs to jointly learn crowd count cl…
Crowd CountingDensity EstimationGeneral ClassificationMulti-Task LearningSolving Jigsaw Puzzles By the Graph Connection Laplacian
We propose a novel mathematical framework to address the problem of automatically solving large jigsaw puzzles. This problem assumes a large image, which is cut into equal square pieces that are arbitrarily rotated and s…
Why Do Accumulated Transformations Extrapolate?
PaTH Attention showed that replacing RoPE's position-indexed rotations with accumulated data-dependent Householder reflections yields strong length extrapolation, though performance degrades at extreme context lengths. W…