paper-with-me

홈 › Papers

Separable Flow: Learning Motion Cost Volumes for Optical Flow Estimation

2021-01-01 · ICCV 2021 10 · Feihu Zhang, Oliver J. Woodford, Victor Adrian Prisacariu, Philip H.S. Torr

Full-motion cost volumes play a central role in current state-of-the-art optical flow methods. However, constructed using simple feature correlations, they lack the ability to encapsulate prior, or even non-local, knowledge. This creates artifacts in poorly constrained, ambiguous regions, such as occluded and textureless areas. We propose a separable cost volume module, a drop-in replacement to correlation cost volumes, that uses non-local aggregation layers to exploit global context cues and prior knowledge, in order to disambiguate motions in these regions. Our method leads both the now standard Sintel and KITTI optical flow benchmarks in terms of accuracy, and is also shown to generalize better from synthetic to real data.

📄 PDF Abstract BibTeX

Code (1)

feihuzhang/separableflow 공식 구현 pytorch

Tasks

Optical Flow Estimation

Similar Papers 제목 키워드 기반

HMAFlow: Learning More Accurate Optical Flow via Hierarchical Motion Field Alignment

2024-09-09 · Dianbo Ma, Kousuke Imamura, Ziyan Gao, Xiangjie Wang 외

Optical flow estimation is a fundamental and long-standing visual task. In this work, we present a novel method, dubbed HMAFlow, to improve optical flow estimation in challenging scenes, particularly those involving smal…

Optical Flow Estimation

EDCFlow: Exploring Temporally Dense Difference Maps for Event-based Optical Flow Estimation

2025-01-01 · CVPR 2025 1 · Daikun Liu, Lei Cheng, Teng Wang, Changyin Sun

Recent learning-based methods for event-based optical flow estimation utilize cost volumes for pixel matching but suffer from redundant computations and limited scalability to higher resolutions for flow refinement. …

Event-based Optical FlowOptical Flow Estimation

Hybrid Cost Volume for Memory-Efficient Optical Flow

2024-09-06 · Yang Zhao, Gangwei Xu, Gang Wu

Current state-of-the-art flow methods are mostly based on dense all-pairs cost volumes. However, as image resolution increases, the computational and spatial complexity of constructing these cost volumes grows at a quart…

4kOptical Flow Estimation

Z-upscaling: Optical Flow Guided Frame Interpolation for Isotropic Reconstruction of 3D EM Volumes

2024-10-09 · Fisseha A. Ferede, Ali Khalighifar, Jaison John, Krishnan Venkataraman 외

We propose a novel optical flow based approach to enhance the axial resolution of anisotropic 3D EM volumes to achieve isotropic 3D reconstruction. Assuming spatial continuity of 3D biological structures in well aligned …

3D ReconstructionOptical Flow EstimationTransfer LearningVideo Frame Interpolation

Removing Cost Volumes from Optical Flow Estimators

2025-10-15 · Simon Kiefhaber, Stefan Roth, Simone Schaub-Meyer arxiv

Cost volumes are used in every modern optical flow estimator, but due to their computational and space complexity, they are often a limiting factor regarding both processing speed and the resolution of input frames. Moti…