[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-151697-en":3,"doc-seo-151697-105":30,"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":4,"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":27,"seo_description":14,"update_tm":28,"read_time":29},151697,2336464648322,"Aria","https://ap-avatar.wpscdn.com/avatar/2200025388227c56fec?_k=1778556882303663488",8,"Research & Report","Image Based Reconstruction of Liquids from 2D Surface Detections - Research paper","A method is proposed for reconstructing liquids from image data using only 2D surface detections represented as binary masks. The approach addresses challenges unique to liquids, where depth and color cues are unreliable due to varying refraction index, opacity, and environmental reflections. A novel particle-based optimization reconstructs the liquid by minimizing rendered surface detection error while enforcing liquid constraints, with solvers that require no training data. A dynamic seeding strategy leverages the previous time step and is evaluated on simulation and two newly released open-source liquid datasets.","Image Based Reconstruction of Liquids from 2D Surface Detections  \nFlorian Richter, Ryan K. Orosco, and Michael C. Yip University of California San Diego  \n{frichter, rorosco, [yip](yip}@ucsd.edu)[}](yip}@ucsd.edu)[@ucsd.edu](yip}@ucsd.edu)  \nAbstract  \nIn this work, we present a solution to the challenging problem of reconstructing liquids from image data. The challenges in reconstructing liquids, which is not faced in previous reconstruction works on rigid and deforming surfaces, lies in the inability to use depth sensing and color features due the variable index of refraction, opacity, and environmental reflections. Therefore, we limit ourselves to only surface detections (i.e. binary mask) of liquids as observations and do not assume any prior knowledge on the liquids properties. A novel optimization problem is posed which reconstructs the liquid as particles by minimizing the error between a rendered surface from the particles and the surface detections while satisfying liquid constraints. Our solvers to this optimization problem are presented and no training data is required to apply them. We also propose a dynamic prediction to seed the reconstruction optimization from the previous time-step. We test our proposed methods in simulation and on two new liquid datasets which we open source 1 so the broader research community can continue developing in this under explored area.  \n1. Introduction  \nTo successfully navigate in and interact with the 3D world we live in, a 3D geometric understanding is required. The importance of this requirement can be seen by the numerous advancements in reconstruction methods from cameras, which is the ideal sensor due to its information richness and cheap cost. Solutions for surface based reconstruction have been proposed for a variety of scenarios such as rigid, unknown environments [31] with dynamic objects [21] . The rigidness assumption has also been lifted to handle deformable surfaces [17, 30] . Breakthrough developments from the reconstruction community have fed into downstream applications such as robotic manipulation [43] and surgical tissue tracking [23] .  \nReconstruction of more complex scenes, such as fluids however remains an under explored area. Fluids, unlike  \n1 [https://github.com/ucsdarclab/liquid_reconstruction](https://github.com/ucsdarclab/liquid_reconstruction)  \nFigure 1 . The top and bottom row figures shows the output of our proposed method for reconstructing liquid from an endoscopic camera and a human pouring chocolate milk into a cup respectively. Our reconstruction approach minimizes the 2D surface detection loss while simultaneously satisfying liquid constraints without the need for any prior training data. The result is an effective reconstruction technique for liquids that has been validated on simulated and real-life data as shown here.  \nrigid and deforming objects, are typically turbulent and can exhibit translating, shearing, and rotation motions [33] . The well established Navier-Stokes equations which describe fluid motion have been applied to generate effective graphic renderings of fluids [4] . The motions of fluids also differs depending on if it is a gas or liquid. Gasses are compressible and reconstruction from images has been explored [9] . Liquids, unlike gasses, are in-compressible and for everyday human interactions, rely on a container and gravity to form their shape (e.g. a mug holding coffee) . By fully reconstructing liquids in 3D, automation efforts which replicate human tasks interacting with liquids can be significantly improved such as robot bar tending [44], autonomous blood suction during surgeries [16], and sewage service [42] . However, the challenge of reconstructing liquids from  \nimages remained unexplored and simplifying heuristics or end-to-end models were used to guide these automation efforts.  \nWe propose an approach to reconstruct and track liquids from videos using minimal information. This results in the first technique to recons","cbCaipLzpYlC1uVd","https://ap.wps.com/l/cbCaipLzpYlC1uVd","pdf",7994817,1,10,"English","en",105,"# Abstract\n# Introduction\n## Motivation for liquid reconstruction\n## Proposed approach and contributions\n# Related Works\n## Fluid Reconstruction","[{\"question\":\"Why is reconstructing liquids from images more difficult than reconstructing rigid or deforming surfaces?\",\"answer\":\"Depth sensing and color features are unreliable for liquids because their appearance changes with refraction index, opacity, and environmental reflections, and common depth sensors behave inconsistently for these reasons.\"},{\"question\":\"What observation data does the proposed method use?\",\"answer\":\"The method uses only 2D surface detections of the liquid as binary masks, without assuming prior knowledge of liquid properties.\"},{\"question\":\"How does the method reconstruct the liquid and what makes it train-free?\",\"answer\":\"It formulates a particle-based optimization that minimizes the error between a rendered particle surface and the detected 2D surface while satisfying liquid constraints. The solvers are presented such that no training data is required to apply them.\"}]","Image Based Reconstruction of Liquids from 2D Surface Detections - Research paper | PDF",1787847545,25,{"code":4,"msg":31,"data":32},"ok",{"site_id":24,"language":23,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":86,"head_meta":88,"extra_data":90,"updated_unix":28},"image-based-reconstruction-of-liquids-from-2d-surface-detections-research-paper","",{"@graph":36,"@context":85},[37,54,68],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,51],{"item":41,"name":42,"@type":43,"position":20},"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/image-based-reconstruction-of-liquids-from-2d-surface-detections-research-paper/151697/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":23,"description":14,"dateModified":62,"datePublished":62,"encodingFormat":61,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-27",true,{"@type":65,"interactionType":66,"userInteractionCount":4},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"Why is reconstructing liquids from images more difficult than reconstructing rigid or deforming surfaces?","Question",{"text":75,"@type":76},"Depth sensing and color features are unreliable for liquids because their appearance changes with refraction index, opacity, and environmental reflections, and common depth sensors behave inconsistently for these reasons.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"What observation data does the proposed method use?",{"text":80,"@type":76},"The method uses only 2D surface detections of the liquid as binary masks, without assuming prior knowledge of liquid properties.",{"name":82,"@type":73,"acceptedAnswer":83},"How does the method reconstruct the liquid and what makes it train-free?",{"text":84,"@type":76},"It formulates a particle-based optimization that minimizes the error between a rendered particle surface and the detected 2D surface while satisfying liquid constraints. The solvers are presented such that no training data is required to apply them.","https://schema.org",{"og:url":52,"og:type":87,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":89,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":92},[93,97,101,105,110,115,120,123,128,131,134],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":46,"category_name":107,"show_sort_weight":108,"slug":109},5,"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":21,"doc_module":4,"doc_module_name":46,"category_name":132,"show_sort_weight":21,"slug":133},"Lifestyle","lifestyle",{"id":135,"doc_module":4,"doc_module_name":46,"category_name":136,"show_sort_weight":106,"slug":137},19,"General","general"]