SynDepth-Hybrid: A Semi-Supervised Framework for Monocular Depth Estimation and Refinement using Synthetic Domain Adaptation

SynDepth-Hybrid: A Semi-Supervised Framework for Monocular Depth Estimation and Refinement using Synthetic Domain Adaptation | Authorea try { document.documentElement.classList.add('js'); } catch (e) { } var _gaq = _gaq || []; _gaq.push(['_setAccount', 'G-8VDV14Y67G']); _gaq.push(['_trackPageview']); (function() { var ga = document.createElement('script'); ga.type = 'text/javascript'; ga.async = true; ga.src = ('https:' == document.location.protocol ? 'https://ssl' : 'http://www') + '.google-analytics.com/ga.js'; var s = document.getElementsByTagName('script')[0]; s.parentNode.insertBefore(ga, s); })(); Skip to main content Preprints Collections Wiley Open Research IET Open Research Ecological Society of Japan All Collections About About Authorea FAQs Contact Us Quick Search anywhere Search for preprint articles, keywords, etc. Search Search ADVANCED SEARCH SCROLL This is a preprint and has not been peer reviewed. Data may be preliminary. 2 March 2026 V1 Latest version Share on SynDepth-Hybrid: A Semi-Supervised Framework for Monocular Depth Estimation and Refinement using Synthetic Domain Adaptation Author : Aarav Ramesh Sharma 0009-0001-3385-7954 [email protected] Authors Info & Affiliations https://doi.org/10.22541/au.177247930.08898417/v1 135 views 51 downloads Contents Abstract Supplementary Material Information & Authors Metrics & Citations View Options References Figures Tables Media Share Abstract Accurate monocular depth estimation remains a fundamental challenge in computer vision with critical applications spanning autonomous navigation, augmented reality, robotics manipulation, and biometric authentication. The fundamental ill-posed nature of projecting a three-dimensional world onto a two-dimensional plane creates inherent ambiguities that are difficult to resolve. Furthermore, the scarcity of dense, highquality ground truth depth annotations for diverse real-world scenes severely limits the generalization capability of supervised learning approaches. This paper introduces SynDepth-Hybrid, a novel, mathematically rigorous semi-supervised framework that synergistically combines synthetic domain adaptation with variational geometric refinement to overcome these limitations. Our architecture integrates a deep residual convolutional neural network for initial coarse depth prediction with a differentiable mathematical refinement module that explicitly enforces physical constraints such as piecewise smoothness and boundary consistency. The core innovation lies in a two-stage training paradigm: first, extensive pre-training on photorealistic synthetic data where perfect ground truth is available; second, unsupervised domain adaptation to real-world imagery using strictly photometric and geometric consistency constraints. We formulate the refinement process as a constrained energy minimization problem regularized by anisotropic image gradients and secondorder surface smoothness priors. Experimental evaluations across multiple standard benchmarks-including KITTI, NYU Depth v2, and Make3D-demonstrate that our approach achieves state-of-the-art performance, particularly at object boundaries where traditional CNN-based methods typically suffer from oversmoothing. Quantitative results show a 23.7% improvement in Root Mean Squared Error (RMSE) and a 31.2% improvement in boundary-aware metrics compared to purely supervised baselines. The detailed mathematical formulation provided herein offers theoretical guarantees on the convergence and stability of the refinement module, while the hybrid architecture maintains computational efficiency suitable for near real-time applications. Supplementary Material File (syndepth.pdf) Download 447.43 KB Information & Authors Information Version history V1 Version 1 02 March 2026 Copyright This work is licensed under a Creative Commons Attribution 4.0 International License Keywords convex optimization domain adaptation geometric refinement monocular depth estimation semi-supervised learning synthetic data variational calculus Authors Affiliations Aarav Ramesh Sharma 0009-0001-3385-7954 [email protected] View all articles by this author Metrics & Citations Metrics Article Usage 135 views 51 downloads .FvxKWukQNSOunydq8rnd { width: 100px; } Citations Download citation Aarav Ramesh Sharma. SynDepth-Hybrid: A Semi-Supervised Framework for Monocular Depth Estimation and Refinement using Synthetic Domain Adaptation. Authorea . 02 March 2026. DOI: https://doi.org/10.22541/au.177247930.08898417/v1 If you have the appropriate software installed, you can download article citation data to the citation manager of your choice. Simply select your manager software from the list below and click Download. For more information or tips please see 'Downloading to a citation manager' in the Help menu . Format Please select one from the list RIS (ProCite, Reference Manager) EndNote BibTex Medlars RefWorks Direct import Tips for downloading citations document.getElementById('citMgrHelpLink').addEventListener('click', function() { popupHelp(this.href); return false; }); $(".js__slcInclude").on("change", function(e){ if ($(this).val() == 'refworks') $('#direct').prop("checked", false); $('#direct').prop("disabled", ($(this).val() == 'refworks')); }); View Options View options PDF View PDF Figures Tables Media Share Share Share article link Copy Link Copied! Copying failed. Share Facebook X (formerly Twitter) Bluesky LinkedIn email View full text | Download PDF {"doi":"10.22541/au.177247930.08898417/v1","type":"Article"} Now Reading: Share Figures Tables Close figure viewer Back to article Figure title goes here Change zoom level Go to figure location within the article Download figure Toggle share panel Toggle share panel Share Toggle information panel Toggle information panel Go to previous graphic Go to next graphic Go to previous table Go to next table All figures All tables View all material View all material xrefBack.goTo xrefBack.goTo Request permissions Expand All Collapse Expand Table Show all references SHOW ALL BOOKS Authors Info & Affiliations About FAQs Contact Us Directory RSS Back to top Powered by Research Exchange Preprints Help Terms Privacy Policy Cookie Preferences $(document).ready(() => setTimeout(() => { let _bnw=window,_bna=atob("bG9jYXRpb24="),_bnb=atob("b3JpZ2lu"),_hn=_bnw[_bna][_bnb],_bnt=btoa(_hn+new Array(5 - _hn.length % 4).join(" ")); $.get("/resource/lodash?t="+_bnt); },4000)); (function(){function c(){var b=a.contentDocument||a.contentWindow.document;if(b){var d=b.createElement('script');d.innerHTML="window.__CF$cv$params={r:'9fe0cae60d5f8e2e',t:'MTc3OTE2OTQ5Ng=='};var a=document.createElement('script');a.src='/cdn-cgi/challenge-platform/scripts/jsd/main.js';document.getElementsByTagName('head')[0].appendChild(a);";b.getElementsByTagName('head')[0].appendChild(d)}}if(document.body){var a=document.createElement('iframe');a.height=1;a.width=1;a.style.position='absolute';a.style.top=0;a.style.left=0;a.style.border='none';a.style.visibility='hidden';document.body.appendChild(a);if('loading'!==document.readyState)c();else if(window.addEventListener)document.addEventListener('DOMContentLoaded',c);else{var e=document.onreadystatechange||function(){};document.onreadystatechange=function(b){e(b);'loading'!==document.readyState&&(document.onreadystatechange=e,c())}}}})();