[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-83624-en":3,"doc-seo-83624-105":29,"detail-sidebar-cat-0-en-105":91},{"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":20,"is_downloadable":20,"audit_status":20,"page_count":21,"language":22,"language_code":23,"site_id":24,"html_lang":23,"table_of_contents":25,"faqs":26,"seo_title":13,"seo_description":14,"update_tm":27,"read_time":28},83624,16904993612988,"Olivia Brown","https://ap-avatar.wpscdn.com/davatar_a8503ba1806abce46bf441b54a3ca4cd",6,"Technology","NeoMap Training-free Novel View Synthesis from Single Images and Videos","Novel-view video synthesis from a single image or monocular video remains difficult due to heavy occlusions, incomplete scene content, and depth ambiguity. Existing approaches rely on camera conditioning, task-specific fine-tuning, or hard stepwise denoising guidance, which often introduces artifacts and weak global scene consistency. NeoMap presents a training-free framework that locates high-fidelity, view-consistent novel views within the native manifold of general pre-trained video models via convergent manifold alternating projection iterations. Experiments on Tanks-and-Temples, LLFF, and DAVIS achieve state-of-the-art fidelity and strong view consistency.","arXiv :2607 .0 1962v 1 [ cs .CV] 2 Jul 2026  \nNeoMap: Training-free Novel-View Synthesis from Single Images and Videos  \nJinxi Li 1 ,2†, Tianyi Zhang 1 ,2†, Yafei Yang 1 ,2, Zihui Zhang 1 ,2, Peng Huang 1 ,2, Koon Wing Macgyver Lin‡, and Bo Yang 1 ,2‡B  \n1 Shenzhen Research Institute, The Hong Kong Polytechnic University  \n2 vLAR Group, The Hong Kong Polytechnic University  \n† equal contribution ‡ joint supervision B corresponding author {[jinxi.li](jinxi.li) ,[tonax.zhang}@connect.polyu.hk](tonax.zhang}@connect.polyu.hk) , [bo.yang@polyu.edu.hk](bo.yang@polyu.edu.hk)  \nAbstract. We study the challenging problem of novel view video synthesis from single images or monocular videos. Existing methods, which operate under the assumption that pre-trained video models lack native novel view synthesis capability and enforce view alignment via camera conditioning, task-specific fine-tuning, or stepwise hard denoising guidance, often suffer from artifacts and compromised global scene consistency. In this paper, we introduce NeoMap, a novel training-free framework designed to locate high-fidelity, view-consistent novel view solutions from general pre-trained video models. The key to our approach is the core insight that promising novel view solutions are inherently encoded within the natural video data manifold learned by pre-trained models, and the core challenge is simply to locate this optimal solution. We solve this via our core mechanism: convergent manifold alternating projection iterations that optimize the initial noise. Extensive experiments demonstrate that NeoMap significantly outperforms all existing methods across  \n3 standard novel view synthesis benchmarks, including the challenging Tanks-and-Temples, LLFF and DAVIS datasets, achieving state-of-theart generation fidelity and top-tier view consistency. Our code and data are available at [https://github.com/vLAR-group/NeoMap](https://github.com/vLAR-group/NeoMap)  \n[Keywords:](Keywords: Novel-view synthesis)[ Novel-view synthesis](Keywords: Novel-view synthesis) · Video generation · Training-free  \n1 Introduction  \nMonocular novel view synthesis (NVS), which generates photorealistic unseen views from a single-view image or unconstrained monocular video, is a core task in computer vision with wide applications in AR/VR, 3D/4D content creation, and robotic perception. However, it remains an extremely challenging problem for traditional reconstruction-based methods [27, 39] due to inherent severe occlusions, incomplete scene information, and depth ambiguity from monocular inputs. Recently, the rapid development of powerful large-scale video generation models [4, 11, 31, 52, 61], which show a reasonable understanding of spatialtemporal relationships, has opened a promising new direction to address this long-standing challenge.  \n2 J. Li et al.  \nFig. 1: Different NVS paradigms: a) Learning new mapping relation would shrink the output data manifold, leading to overfitting and OOD problem; b) Guiding generation trajectory with bad condition would lead the generation output away from data manifold; c) Different related output possibilities already exist in the data manifold.  \nOne line of work learns a new conditional video generation mapping by training models on 3D/4D data with camera pose annotations. Either injecting camera trajectories [2,3,56,58] or taking depth-based warped view images [12,58,64] as additional generation conditions, these methods essentially constrain the denoising process with pose-related signals. Although these methods show promising performance, they inevitably suffer from overfitting to limited camera trajectory distributions and depth estimation noise seen during training, leading to poor generalization to in-the-wild scenes and unseen camera motions. Another line of work avoids task-specific retraining via training-free guidance strategies [49, 62] . They use depth-based warped images as reliable priors, and blend the latent features of priors with t","cbCaiiEpEWtQ9EWH","https://ap.wps.com/l/cbCaiiEpEWtQ9EWH","pdf",17785174,1,30,"English","en",105,"# Introduction\n## Problem motivation and challenges\n## Related work and limitations\n## Core insight behind NeoMap\n# Method overview","[{\"question\":\"What problem does NeoMap address?\",\"answer\":\"NeoMap targets training-free novel-view video synthesis, generating photorealistic unseen views from a single image or monocular video.\"},{\"question\":\"Why do existing methods often produce artifacts?\",\"answer\":\"Prior work typically depends on camera conditioning, fine-tuning, or hard stepwise guidance that can disrupt the native generation trajectory, leading to artifacts and compromised global consistency.\"},{\"question\":\"How does NeoMap find valid novel views without training?\",\"answer\":\"NeoMap searches for the optimal initial noise latent that corresponds to a high-quality target within the pre-trained model’s native output data manifold, using convergent manifold alternating projection iterations.\"}]",1784189349,76,{"code":4,"msg":30,"data":31},"ok",{"site_id":24,"language":23,"slug":32,"title":13,"keywords":33,"description":14,"schema_data":34,"social_meta":86,"head_meta":88,"extra_data":90,"updated_unix":27},"neomap-training-free-novel-view-synthesis-from-single-images-and-videos","",{"@graph":35,"@context":85},[36,53,68],{"@type":37,"itemListElement":38},"BreadcrumbList",[39,43,47,50],{"item":40,"name":41,"@type":42,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":44,"name":45,"@type":42,"position":46},"https://docshare.wps.com/document/","Document",2,{"item":48,"name":12,"@type":42,"position":49},"https://docshare.wps.com/document/technology/",3,{"item":51,"name":13,"@type":42,"position":52},"https://docshare.wps.com/document/neomap-training-free-novel-view-synthesis-from-single-images-and-videos/83624/",4,{"url":51,"name":13,"@type":54,"author":55,"headline":13,"publisher":57,"fileFormat":60,"inLanguage":23,"description":14,"dateModified":61,"datePublished":62,"encodingFormat":60,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":56},"Person",{"url":40,"name":58,"@type":59},"DocShare","Organization","application/pdf","2026-07-17","2026-07-16",true,{"@type":65,"interactionType":66,"userInteractionCount":20},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"What problem does NeoMap address?","Question",{"text":75,"@type":76},"NeoMap targets training-free novel-view video synthesis, generating photorealistic unseen views from a single image or monocular video.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"Why do existing methods often produce artifacts?",{"text":80,"@type":76},"Prior work typically depends on camera conditioning, fine-tuning, or hard stepwise guidance that can disrupt the native generation trajectory, leading to artifacts and compromised global consistency.",{"name":82,"@type":73,"acceptedAnswer":83},"How does NeoMap find valid novel views without training?",{"text":84,"@type":76},"NeoMap searches for the optimal initial noise latent that corresponds to a high-quality target within the pre-trained model’s native output data manifold, using convergent manifold alternating projection iterations.","https://schema.org",{"og:url":51,"og:type":87,"og:title":13,"og:site_name":58,"og:description":14},"article",{"robots":89,"canonical":51},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":92},[93,97,101,105,110,113,118,122,127,130,134],{"id":20,"doc_module":4,"doc_module_name":45,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":46,"doc_module":4,"doc_module_name":45,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":52,"doc_module":4,"doc_module_name":45,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":45,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":11,"doc_module":4,"doc_module_name":45,"category_name":12,"show_sort_weight":111,"slug":112},50,"technology",{"id":114,"doc_module":4,"doc_module_name":45,"category_name":115,"show_sort_weight":116,"slug":117},7,"Healthcare",40,"healthcare",{"id":119,"doc_module":4,"doc_module_name":45,"category_name":120,"show_sort_weight":21,"slug":121},8,"Research & Report","research-report",{"id":123,"doc_module":4,"doc_module_name":45,"category_name":124,"show_sort_weight":125,"slug":126},9,"Religion & Spirituality",20,"religion-spirituality",{"id":125,"doc_module":4,"doc_module_name":45,"category_name":128,"show_sort_weight":125,"slug":129},"World Cup","world-cup",{"id":131,"doc_module":4,"doc_module_name":45,"category_name":132,"show_sort_weight":131,"slug":133},10,"Lifestyle","lifestyle",{"id":135,"doc_module":4,"doc_module_name":45,"category_name":136,"show_sort_weight":106,"slug":137},19,"General","general"]