[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-86312-en":3,"doc-seo-86312-105":30,"detail-sidebar-cat-0-en-105":92},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":20,"is_deleted":4,"is_public":21,"is_downloadable":21,"audit_status":21,"page_count":22,"language":23,"language_code":24,"site_id":25,"html_lang":24,"table_of_contents":26,"faqs":27,"seo_title":13,"seo_description":14,"update_tm":28,"read_time":29},86312,13056703020460,"Valentina","https://ap-avatar.wpscdn.com/avatar/be000253dac470eee5d?_k=1778207105932848923",8,"Research & Report","SVI360: Spherical Video Interpolation","Omnidirectional video interpolation is critical for applications such as virtual reality and immersive video enhancement, yet existing video interpolation methods struggle with severe spherical distortions near the poles. SVI360 introduces a dual-branch framework that combines an original frame with a rotated orthogonal view. By reinforcing equivariance of flow displacements across the two views, the method improves intermediate frame prediction while preserving high-fidelity optical flow. Experiments show state-of-the-art interpolation quality on four public benchmarks with available code and pretrained models.","1  \n[ cs .CV] 13 Jul 2026  \nSVI360: Spherical Video Interpolation  \nLe-Kim Nguyen 1, Renato Martins 1,  \nPascal Vasseur2, and Cedric Demonceaux 1  \n1 Université Bourgogne Europe, ICB UMR 6303 CNRS, France  \n2 Université de Picardie Jules Verne, MIS UR 4290, France  \nAbstract. This paper addresses the problem of omnidirectional video interpolation, which plays an essential role in applications such as virtual reality and immersive video enhancement. Existing video interpolation methods are not well-suited for spherical videos, as they have difficulty handling severe distortions close to the poles. To address this issue, we propose SVI360, a dual-branch framework that combines the image frame and its rotated orthogonal view to deal with these distortions. The core methodological aspect of the approach is to reinforce equivariance of the flow displacements between the original and orthogonal views to improve intermediate frame prediction. Experiments show that our method outperforms state-of-the-art approaches in interpolation quality while maintaining accurate optical flow in four different public benchmarks. Code and pre-trained models are available at:  \n[https://icb-vision-ai.github.io/video360_interpolation/](https://icb-vision-ai.github.io/video360_interpolation/)  \nKeywords: Video frame interpolation · Omnidirectional images · Spherical optical flow estimation.  \nIntroduction  \n2 Nguyen et al.  \nFig. 1: Limitations of perspective video interpolation methods on spherical images. Red boxes indicate regions where existing methods produce severe ghosting and blurring, whereas the proposed approach better preserves fine image details.  \nCompared with typical perspective images, spherical data introduce severe geometric distortions, non-uniform pixel density, and large pixel flow displacements. These characteristics make correspondence estimation and motion reconstruction considerably more challenging, emphasizing the need for architectures designed to handle spherical data. Despite the growing importance of 360 ◦ video, omnidirectional video interpolation methods remain clearly overlooked. In this context, 360VFI [15] is the first method and benchmark dedicated to 360◦ frame interpolation. It introduces a distortion-aware design that uses spherical geometry priors for feature extraction and fusion, and provides an evaluation protocol based on flow magnitude. They stratified the test set into four distinct settings based on the vertical flow magnitude, where the flow may result from object motion and camera movement. In the Easy settings, characterized by very small pixel displacement between two frames (average flow magnitude \u003C2), the method can perform well. However, as the flow magnitude increases, the performance drops significantly, indicating that the approach still has limitations in handling large pixel displacements. In this work, we introduce SVI360, a novel video interpolation approach designed to improve the fidelity of interpolated frames while maintaining high-quality optical flow estimation, particularly in image regions containing larger distortions.  \nOur method adopts a coarse-to-fine base strategy with progressively increasing resolutions, inspired by AMT [13], where intermediate optical flows and intermediate frame features are iteratively refined using dense all-pairs bidirectional correlation volumes. To adapt this concept to spherical geometry, we incorporate the key hypothesis from PriOr-Flow [14], which suggests that generating orthogonal views of spherical images can provide complementary priors that improve optical flow estimation in the primitive (original) spherical view. Based on this insight, we design a dual-branch architecture where the orthogonal branch refines both the optical flow and the interpolated frame in the primitive branch through cross-view feature interaction, yielding more accurate frame interpolations in four widely adopted public datasets: two synthetic datasets (FlowScape [21] an","cbCaijFOtnvijmAh","https://ap.wps.com/l/cbCaijFOtnvijmAh","pdf",34722593,5,1,27,"English","en",105,"# Introduction\n## Challenges of perspective vs. spherical video\n## Related work on 360° frame interpolation\n# Method: SVI360\n## Dual-branch architecture with orthogonal view\n## Coarse-to-fine refinement and correlation volumes\n# Contributions\n## Equivariance-guided optical flow and frame interpolation\n## Spherical Weighted Charbonnier loss\n## Benchmark evaluations and results","[{\"question\":\"What problem does SVI360 address in omnidirectional video interpolation?\",\"answer\":\"It addresses poor performance of existing interpolation methods on spherical videos, especially severe distortions and large pixel displacements near the poles.\"},{\"question\":\"How does SVI360 improve intermediate frame prediction?\",\"answer\":\"It uses a dual-branch design that integrates the original frame with a rotated orthogonal view, reinforcing equivariance of flow displacements between the two views.\"},{\"question\":\"What evidence shows SVI360 outperforms prior approaches?\",\"answer\":\"Experiments report higher interpolation quality than state-of-the-art methods across four public benchmarks, while maintaining accurate optical flow on reported metrics.\"}]",1784210414,68,{"code":4,"msg":31,"data":32},"ok",{"site_id":25,"language":24,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":87,"head_meta":89,"extra_data":91,"updated_unix":28},"svi360-spherical-video-interpolation","",{"@graph":36,"@context":86},[37,54,69],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,51],{"item":41,"name":42,"@type":43,"position":21},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":47},"https://docshare.wps.com/document/","Document",2,{"item":49,"name":12,"@type":43,"position":50},"https://docshare.wps.com/document/research-report/",3,{"item":52,"name":13,"@type":43,"position":53},"https://docshare.wps.com/document/svi360-spherical-video-interpolation/86312/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":24,"description":14,"dateModified":62,"datePublished":63,"encodingFormat":61,"isAccessibleForFree":64,"interactionStatistic":65},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-07-25","2026-07-16",true,{"@type":66,"interactionType":67,"userInteractionCount":20},"InteractionCounter",{"@type":68},"ViewAction",{"@type":70,"mainEntity":71},"FAQPage",[72,78,82],{"name":73,"@type":74,"acceptedAnswer":75},"What problem does SVI360 address in omnidirectional video interpolation?","Question",{"text":76,"@type":77},"It addresses poor performance of existing interpolation methods on spherical videos, especially severe distortions and large pixel displacements near the poles.","Answer",{"name":79,"@type":74,"acceptedAnswer":80},"How does SVI360 improve intermediate frame prediction?",{"text":81,"@type":77},"It uses a dual-branch design that integrates the original frame with a rotated orthogonal view, reinforcing equivariance of flow displacements between the two views.",{"name":83,"@type":74,"acceptedAnswer":84},"What evidence shows SVI360 outperforms prior approaches?",{"text":85,"@type":77},"Experiments report higher interpolation quality than state-of-the-art methods across four public benchmarks, while maintaining accurate optical flow on reported metrics.","https://schema.org",{"og:url":52,"og:type":88,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":90,"canonical":52},"index,follow",{"doc_id":7,"site_id":25},{"code":4,"msg":5,"data":93},[94,98,102,106,110,115,120,123,128,131,135],{"id":21,"doc_module":4,"doc_module_name":46,"category_name":95,"show_sort_weight":96,"slug":97},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":99,"show_sort_weight":100,"slug":101},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":103,"show_sort_weight":104,"slug":105},"Exam",70,"exam",{"id":20,"doc_module":4,"doc_module_name":46,"category_name":107,"show_sort_weight":108,"slug":109},"Comic",60,"comic",{"id":111,"doc_module":4,"doc_module_name":46,"category_name":112,"show_sort_weight":113,"slug":114},6,"Technology",50,"technology",{"id":116,"doc_module":4,"doc_module_name":46,"category_name":117,"show_sort_weight":118,"slug":119},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":121,"slug":122},30,"research-report",{"id":124,"doc_module":4,"doc_module_name":46,"category_name":125,"show_sort_weight":126,"slug":127},9,"Religion & Spirituality",20,"religion-spirituality",{"id":126,"doc_module":4,"doc_module_name":46,"category_name":129,"show_sort_weight":126,"slug":130},"World Cup","world-cup",{"id":132,"doc_module":4,"doc_module_name":46,"category_name":133,"show_sort_weight":132,"slug":134},10,"Lifestyle","lifestyle",{"id":136,"doc_module":4,"doc_module_name":46,"category_name":137,"show_sort_weight":20,"slug":138},19,"General","general"]