Learning to Extract Motion from Videos in Convolutional Neural Networks
원문 초록
This paper shows how to extract dense optical flow from videos with a convolutional neural network (CNN). The proposed model constitutes a potential building block for deeper architectures to allow using motion without resorting to an external algorithm, \eg for recognition in videos. We derive our network architecture from signal processing principles to provide desired invariances to image contrast, phase and texture. We constrain weights within the network to enforce strict rotation invariance and substantially reduce the number of parameters to learn. We demonstrate end-to-end training on only 8 sequences of the Middlebury dataset, orders of magnitude less than competing CNN-based motion estimation methods, and obtain comparable performance to classical methods on the Middlebury benchmark. Importantly, our method outputs a distributed representation of motion that allows representing multiple, transparent motions, and dynamic textures. Our contributions on network design and rotation invariance offer insights nonspecific to motion estimation.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
EndoMUST: Monocular Depth Estimation for Robotic Endoscopy via End-to-end Multi-step Self-supervised Training
Spatio-Temporal State Space Model For Efficient Event-Based Optical Flow
Event-Enhanced Blurry Video Super-Resolution
ReynoldsFlow: Exquisite Flow Estimation via Reynolds Transport Theorem
EventDiff: A Unified and Efficient Diffusion Model Framework for Event-based Video Frame Interpolation
TimeTracker: Event-based Continuous Point Tracking for Video Frame Interpolation with Non-linear Motion
토론
이 논문과 연결된 포럼 글이 아직 없습니다.