{"id":32479,"date":"2026-01-21T17:02:02","date_gmt":"2026-01-21T17:02:02","guid":{"rendered":"https:\/\/lamarr-institute.org\/publication\/slcf-net-sequential-lidar-camera-fusion-for-semantic-scene-completion-using-a-3d-recurrent-u-net\/"},"modified":"2026-06-08T13:20:43","modified_gmt":"2026-06-08T13:20:43","slug":"slcf-net-sequential-lidar-camera-fusion-for-semantic-scene-completion-using-a-3d-recurrent-u-net","status":"publish","type":"publication","link":"https:\/\/lamarr-institute.org\/de\/publication\/slcf-net-sequential-lidar-camera-fusion-for-semantic-scene-completion-using-a-3d-recurrent-u-net\/","title":{"rendered":"SLCF-Net: Sequential LiDAR-Camera Fusion for Semantic Scene Completion using a 3D Recurrent U-Net"},"content":{"rendered":"<p>We introduce SLCF-Net, a novel approach for the Semantic Scene Completion (SSC) task that sequentially fuses LiDAR and camera data. It jointly estimates missing geometry and semantics in a scene from sequences of RGB images and sparse LiDAR measurements. The images are semantically segmented by a pre-trained 2D U-Net and a dense depth prior is estimated from a depth-conditioned pipeline fueled by Depth Anything. To associate the 2D image features with the 3D scene volume, we introduce Gaussian-decay Depth-prior Projection (GDP). This module projects the 2D features into the 3D volume along the line of sight with a Gaussian-decay function, centered around the depth prior. Volumetric semantics is computed by a 3D U-Net. We propagate the hidden 3D U-Net state using the sensor motion and design a novel loss to ensure temporal consistency. We evaluate our approach on the SemanticKITTI dataset and compare it with leading SSC approaches. The SLCF-Net excels in all SSC metrics and shows great temporal consistency.<\/p>\n","protected":false},"excerpt":{"rendered":"<p>We introduce SLCF-Net, a novel approach for the Semantic Scene Completion (SSC) task that sequentially fuses LiDAR and camera data. It jointly estimates missing geometry and semantics in a scene from sequences of RGB images and sparse LiDAR measurements. The images are semantically segmented by a pre-trained 2D U-Net and a dense depth prior is estimated from a depth-conditioned pipeline fueled by Depth Anything. To associate the 2D image features [&hellip;]<\/p>\n","protected":false},"author":12,"featured_media":0,"template":"","meta":{"_acf_changed":false,"footnotes":""},"publication-type":[32],"class_list":["post-32479","publication","type-publication","status-publish","hentry","publication-type-inproceedings"],"acf":[],"publishpress_future_workflow_manual_trigger":{"enabledWorkflows":[]},"_links":{"self":[{"href":"https:\/\/lamarr-institute.org\/de\/wp-json\/wp\/v2\/publication\/32479","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\/32479\/revisions"}],"wp:attachment":[{"href":"https:\/\/lamarr-institute.org\/de\/wp-json\/wp\/v2\/media?parent=32479"}],"wp:term":[{"taxonomy":"publication-type","embeddable":true,"href":"https:\/\/lamarr-institute.org\/de\/wp-json\/wp\/v2\/publication-type?post=32479"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}