Pyramid-angular-constraint network for light field super-resolutionOA
Light field(LF)cameras record both intensity and directions of light rays in a scene with a single exposure.Due to the trade-off between spatial and angular dimensions,the spatial resolution of LF images is limited,so super-resolution is widely studied.Pixels follow linear coordinate projection across views in LF images.Hence,auxiliary views nearer to the target view are generally more effective for use in super-resolution.In this paper,an LF-pyramid is proposed based on an angular-distance constraint for discriminatively exploiting auxiliary views.From views of different layers in an LF-pyramid,complementary features of different effectiveness can be extracted.However,shapes of LF-pyramids change for target views with different angular positions.To fully exploit an LF-pyramid,we introduce a pyramid-angular-constraint network for LF super-resolution(LF-PACNet).Specifically,to handle an arbitrary number of views in each layer,an intrapyramid-layer feature extraction module is designed,which treats all views in the same layer equally in complementary information extraction.Then,to deal with an arbitrary number of layers,a recurrent cross-pyramid-layer feature complementation module is constructed,which discriminatively complements the target view with high-frequency details.Extensive experiments on public datasets demonstrate state-ofthe-art performance for our method,both visually and numerically,especially for datasets with large disparities.
Da Yang;Hao Sheng;Sizhe Wang;Wei Ke;Zhang Xiong
Data Science and Intelligent Computing Laboratory,Hangzhou International Innovation Institute,Beihang University,Hangzhou 311115,China State Key Laboratory of Virtual Reality Technology and Systems,School of Computer Science and Engineering,Beihang University,Beijing 100191,China Faculty of Applied Sciences,Macao Polytechnic University,Macao SAR 999078,ChinaData Science and Intelligent Computing Laboratory,Hangzhou International Innovation Institute,Beihang University,Hangzhou 311115,China State Key Laboratory of Virtual Reality Technology and Systems,School of Computer Science and Engineering,Beihang University,Beijing 100191,China Faculty of Applied Sciences,Macao Polytechnic University,Macao SAR 999078,ChinaData Science and Intelligent Computing Laboratory,Hangzhou International Innovation Institute,Beihang University,Hangzhou 311115,China State Key Laboratory of Virtual Reality Technology and Systems,School of Computer Science and Engineering,Beihang University,Beijing 100191,China Faculty of Applied Sciences,Macao Polytechnic University,Macao SAR 999078,ChinaFaculty of Applied Sciences,Macao Polytechnic University,Macao SAR 999078,ChinaData Science and Intelligent Computing Laboratory,Hangzhou International Innovation Institute,Beihang University,Hangzhou 311115,China State Key Laboratory of Virtual Reality Technology and Systems,School of Computer Science and Engineering,Beihang University,Beijing 100191,China Faculty of Applied Sciences,Macao Polytechnic University,Macao SAR 999078,China
信息技术与安全科学
light field(LF)super-resolutioncross-view differenceangular–distance constraintdiscriminative complementation
《Computational Visual Media》 2026 (1)
P.221-242,22
supported by the National Key R&D Program of China(2022YFC3803600)the National Natural Science Foundation of China(62372023)the Open Fund of the State Key Laboratory of Software Development Environment(SKLSDE-2023ZX-11)We also thank the HAWKEYE Group for support.
评论