{"id":36538,"date":"2026-06-08T13:16:40","date_gmt":"2026-06-08T13:16:40","guid":{"rendered":"https:\/\/lamarr-institute.org\/publication\/monoem-gs-monocular-expectation-maximization-gaussian-splatting-slam\/"},"modified":"2026-06-08T13:16:40","modified_gmt":"2026-06-08T13:16:40","slug":"monoem-gs-monocular-expectation-maximization-gaussian-splatting-slam","status":"publish","type":"publication","link":"https:\/\/lamarr-institute.org\/de\/publication\/monoem-gs-monocular-expectation-maximization-gaussian-splatting-slam\/","title":{"rendered":"{MonoEM}-{GS}: Monocular Expectation-Maximization Gaussian Splatting {SLAM}"},"content":{"rendered":"<p>Feed-forward geometric foundation models can infer dense point clouds and camera motion directly from {RGB} streams, providing priors for monocular {SLAM}. However, their predictions are often view-dependent and noisy: geometry can vary across viewpoints and under image transformations, and local metric properties may drift between frames. We present {MonoEM}-{GS}, a monocular mapping pipeline that integrates such geometric predictions into a global Gaussian Splatting representation while explicitly addressing these inconsistencies. {MonoEM}-{GS} couples Gaussian Splatting with an Expectation&#8211;Maximization formulation to stabilize geometry, and employs {ICP}-based alignment for monocular pose estimation. Beyond geometry, {MonoEM}-{GS} parameterizes Gaussians with multi-modal features, enabling in-place open-set segmentation and other downstream queries directly on the reconstructed map. We evaluate {MonoEM}-{GS} on 7-Scenes, {TUM} {RGB}-D and Replica, and compare against recent baselines.<\/p>\n","protected":false},"excerpt":{"rendered":"<p>Feed-forward geometric foundation models can infer dense point clouds and camera motion directly from {RGB} streams, providing priors for monocular {SLAM}. However, their predictions are often view-dependent and noisy: geometry can vary across viewpoints and under image transformations, and local metric properties may drift between frames. We present {MonoEM}-{GS}, a monocular mapping pipeline that integrates such geometric predictions into a global Gaussian Splatting representation while explicitly addressing these inconsistencies. {MonoEM}-{GS} [&hellip;]<\/p>\n","protected":false},"author":12,"featured_media":0,"template":"","meta":{"_acf_changed":false,"footnotes":""},"publication-type":[30],"class_list":["post-36538","publication","type-publication","status-publish","hentry","publication-type-article"],"acf":[],"publishpress_future_workflow_manual_trigger":{"enabledWorkflows":[]},"_links":{"self":[{"href":"https:\/\/lamarr-institute.org\/de\/wp-json\/wp\/v2\/publication\/36538","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/lamarr-institute.org\/de\/wp-json\/wp\/v2\/publication"}],"about":[{"href":"https:\/\/lamarr-institute.org\/de\/wp-json\/wp\/v2\/types\/publication"}],"author":[{"embeddable":true,"href":"https:\/\/lamarr-institute.org\/de\/wp-json\/wp\/v2\/users\/12"}],"version-history":[{"count":0,"href":"https:\/\/lamarr-institute.org\/de\/wp-json\/wp\/v2\/publication\/36538\/revisions"}],"wp:attachment":[{"href":"https:\/\/lamarr-institute.org\/de\/wp-json\/wp\/v2\/media?parent=36538"}],"wp:term":[{"taxonomy":"publication-type","embeddable":true,"href":"https:\/\/lamarr-institute.org\/de\/wp-json\/wp\/v2\/publication-type?post=36538"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}