Hierarchical Spatial Transformer Network
Computer vision researchers have been expecting that neural networks have spatial transformation ability to eliminate the interference caused by geometric distortion for a long time. Emergence of spatial transformer network makes dream come true. Spatial transformer network and its variants can handle global displacement well, but lack the ability to deal with local spatial variance. Hence how to achieve a better manner of deformation in the neural network has become a pressing matter of the moment. To address this issue, we analyze the advantages and disadvantages of approximation theory and optical flow theory, then we combine them to propose a novel way to achieve image deformation and implement it with a hierarchical convolutional neural network. This new approach solves for a linear deformation along with an optical flow field to model image deformation. In the experiments of cluttered MNIST handwritten digits classification and image plane alignment, our method outperforms baseline methods by a large margin.
Code (0)
등록된 구현이 없습니다.
Tasks
Optical Flow EstimationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
HSPFormer: Hierarchical Spatial Perception Transformer for Semantic Segmentation
Semantic perception in driving scenarios plays a crucial role in intelligent transportation systems. However, existing Transformer-based semantic segmentation methods often do not fully exploit their potential in underst…
Depth EstimationMonocular Depth EstimationSemantic SegmentationSpatial ReasoningHSTFormer: Hierarchical Spatial-Temporal Transformers for 3D Human Pose Estimation
Transformer-based approaches have been successfully proposed for 3D human pose estimation (HPE) from 2D pose sequence and achieved state-of-the-art (SOTA) performance. However, current SOTAs have difficulties in modeling…
3D Human Pose EstimationPose EstimationDisentangled Diffusion-Based 3D Human Pose Estimation with Hierarchical Spatial and Temporal Denoiser
Recently, diffusion-based methods for monocular 3D human pose estimation have achieved state-of-the-art (SOTA) performance by directly regressing the 3D joint coordinates from the 2D pose sequence. Although some methods …
3D Human Pose EstimationDisentanglementMonocular 3D Human Pose EstimationMulti-Hypotheses 3D Human Pose Estimation+1HiT-SR: Hierarchical Transformer for Efficient Image Super-Resolution
Transformers have exhibited promising performance in computer vision tasks including image super-resolution (SR). However, popular transformer-based SR methods often employ window self-attention with quadratic computatio…
Image Super-ResolutionSuper-ResolutionSTMT: A Spatial-Temporal Mesh Transformer for MoCap-Based Action Recognition
We study the problem of human action recognition using motion capture (MoCap) sequences. Unlike existing techniques that take multiple manual steps to derive standardized skeleton representations as model input, we propo…
Action RecognitionTemporal Action Localization