{"id":{"repo_id":"calpoly","oai_identifier":"oai:digitalcommons.calpoly.edu:theses-5041"},"canonical_url":"https://search.ndltd.org/etd/calpoly/oai:digitalcommons.calpoly.edu:theses-5041","repository":{"repo_id":"calpoly","name":"Cal Poly","base_url":"https://digitalcommons.calpoly.edu/do/oai/"},"display":{"title":"Uncertainty-Weighted Fusion of Sensor and Monocular Foundation-Model Depth for 3D Gaussian Splatting in Indoor RGB-D Capture","abstract":"Depth-supervised 3D Gaussian Splatting can improve scene geometry in indoor RGB-D capture, but noisy commodity depth measurements can also reduce rendered image quality. This thesis studies that trade-off in room-scale indoor reconstruction using two complementary depth sources: Kinect-class RGB-D sensor depth, which is metric but noisy and incomplete, and Depth Anything 3 (DA3) monocular depth, which is dense and meter-valued but not calibrated to the sensor or laser-reference geometry. The proposed method constructs a per-pixel depth supervision target by inverse-variance fusion of the sensor depth and the monocular depth prediction. The fused target is used to train a depth-supervised 3D Gaussian Splatting model built on DN-Splatter. Two uncertainty models are evaluated: an implementation-based heuristic, using a configured Kinect noise floor and DA3 depth-structure terms, and a learned-confidence variant, using DA3's native reliability output. The method is evaluated on ten MuSHRoom indoor scenes under held-out Kinect depth metrics, with independent FARO point-cloud and per-frame depth protocols used for additional geometry validation. Across the ten-room MuSHRoom evaluation, heuristic fusion improves RGB quality over sensor-only supervision in all 10 rooms, with mean improvements of 0.42 dB PSNR and 0.009 SSIM and a mean LPIPS reduction of 0.012. Kinect-evaluated geometry stays close to sensor-only supervision with a near-zero median AbsRel increase of 0.0009. FARO-based evaluation supports the same overall geometry conclusion while identifying one point-cloud completeness outlier. The DA3 learned-confidence variant gives mixed appearance changes but consistently worse geometry, showing that a foundation model's internal confidence is not automatically the right uncertainty model for metric fusion. These results support uncertainty-weighted sensor-plus-monocular depth fusion as a practical supervision strategy for indoor 3D Gaussian Splatting.","abstract_html":"Depth-supervised 3D Gaussian Splatting can improve scene geometry in indoor RGB-D capture, but noisy commodity depth measurements can also reduce rendered image quality. This thesis studies that trade-off in room-scale indoor reconstruction using two complementary depth sources: Kinect-class RGB-D sensor depth, which is metric but noisy and incomplete, and Depth Anything 3 (DA3) monocular depth, which is dense and meter-valued but not calibrated to the sensor or laser-reference geometry. The proposed method constructs a per-pixel depth supervision target by inverse-variance fusion of the sensor depth and the monocular depth prediction. The fused target is used to train a depth-supervised 3D Gaussian Splatting model built on DN-Splatter. Two uncertainty models are evaluated: an implementation-based heuristic, using a configured Kinect noise floor and DA3 depth-structure terms, and a learned-confidence variant, using DA3&#x27;s native reliability output. The method is evaluated on ten MuSHRoom indoor scenes under held-out Kinect depth metrics, with independent FARO point-cloud and per-frame depth protocols used for additional geometry validation. Across the ten-room MuSHRoom evaluation, heuristic fusion improves RGB quality over sensor-only supervision in all 10 rooms, with mean improvements of 0.42 dB PSNR and 0.009 SSIM and a mean LPIPS reduction of 0.012. Kinect-evaluated geometry stays close to sensor-only supervision with a near-zero median AbsRel increase of 0.0009. FARO-based evaluation supports the same overall geometry conclusion while identifying one point-cloud completeness outlier. The DA3 learned-confidence variant gives mixed appearance changes but consistently worse geometry, showing that a foundation model&#x27;s internal confidence is not automatically the right uncertainty model for metric fusion. These results support uncertainty-weighted sensor-plus-monocular depth fusion as a practical supervision strategy for indoor 3D Gaussian Splatting.","abstract_has_math":false,"creators":["Howell, Brandon S"],"institution":null,"degree_name":"MS in Computer Science","degree_level":null,"degree_discipline":"Computer Science","degree_department":null,"school":null,"contributors":["Jonathan Ventura","Computer Science","College of Engineering"],"advisors":[],"committee_chairs":[],"committee_members":[],"year":null,"date_issued":"","date_published":null,"updated_at":"2026-11-19T07:12:58Z","subjects":["Gaussian Splatting","depth fusion","RGB-D","monocular depth estimation","indoor scene reconstruction"],"languages":[],"rights":[],"rights_urls":[],"identifier_entries":[],"person_identifier_entries":[]},"links":{"outbound_url":"https://digitalcommons.calpoly.edu/theses/3347","outbound_label":"Repository record","outbound_source":"dc:identifier","record_url":"https://digitalcommons.calpoly.edu/theses/3347","record_label":"Repository record","record_kind":"record","record_source":"dc:identifier","download_url":null,"download_label":null,"download_source":null,"access_status":null,"embargo_until":null,"access_note":null},"source_record":{"url":"https://digitalcommons.calpoly.edu/do/oai/?verb=GetRecord&metadataPrefix=oai_etdms&identifier=oai%3Adigitalcommons.calpoly.edu%3Atheses-5041","prefix":"oai_etdms"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Jonathan Ventura","Computer Science","College of Engineering"]},{"key":"dc:creator","label":"Author","values":["Howell, Brandon S"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.available","label":"Dc Date Available","values":["2026-06-12T07:00:00Z"]},{"key":"dc:date.created","label":"Dc Date Created","values":["2026-06-01T07:00:00Z"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["Computer Science"]},{"key":"thesis:degree_name","label":"Degree Name","values":["MS in Computer Science"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["Gaussian Splatting","depth fusion","RGB-D","monocular depth estimation","indoor scene reconstruction"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["https://digitalcommons.calpoly.edu/theses/3347"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["Depth-supervised 3D Gaussian Splatting can improve scene geometry in indoor RGB-D capture, but noisy commodity depth measurements can also reduce rendered image quality. This thesis studies that trade-off in room-scale indoor reconstruction using two complementary depth sources: Kinect-class RGB-D sensor depth, which is metric but noisy and incomplete, and Depth Anything 3 (DA3) monocular depth, which is dense and meter-valued but not calibrated to the sensor or laser-reference geometry. The proposed method constructs a per-pixel depth supervision target by inverse-variance fusion of the sensor depth and the monocular depth prediction. The fused target is used to train a depth-supervised 3D Gaussian Splatting model built on DN-Splatter. Two uncertainty models are evaluated: an implementation-based heuristic, using a configured Kinect noise floor and DA3 depth-structure terms, and a learned-confidence variant, using DA3's native reliability output. The method is evaluated on ten MuSHRoom indoor scenes under held-out Kinect depth metrics, with independent FARO point-cloud and per-frame depth protocols used for additional geometry validation. Across the ten-room MuSHRoom evaluation, heuristic fusion improves RGB quality over sensor-only supervision in all 10 rooms, with mean improvements of 0.42 dB PSNR and 0.009 SSIM and a mean LPIPS reduction of 0.012. Kinect-evaluated geometry stays close to sensor-only supervision with a near-zero median AbsRel increase of 0.0009. FARO-based evaluation supports the same overall geometry conclusion while identifying one point-cloud completeness outlier. The DA3 learned-confidence variant gives mixed appearance changes but consistently worse geometry, showing that a foundation model's internal confidence is not automatically the right uncertainty model for metric fusion. These results support uncertainty-weighted sensor-plus-monocular depth fusion as a practical supervision strategy for indoor 3D Gaussian Splatting."]},{"key":"dc:title","label":"Title","values":["Uncertainty-Weighted Fusion of Sensor and Monocular Foundation-Model Depth for 3D Gaussian Splatting in Indoor RGB-D Capture"]}]}],"canonical_facts":{"dc:contributor":["Jonathan Ventura","Computer Science","College of Engineering"],"dc:creator":["Howell, Brandon S"],"dc:date.available":["2026-06-12T07:00:00Z"],"dc:date.created":["2026-06-01T07:00:00Z"],"dc:description.abstract":["Depth-supervised 3D Gaussian Splatting can improve scene geometry in indoor RGB-D capture, but noisy commodity depth measurements can also reduce rendered image quality. This thesis studies that trade-off in room-scale indoor reconstruction using two complementary depth sources: Kinect-class RGB-D sensor depth, which is metric but noisy and incomplete, and Depth Anything 3 (DA3) monocular depth, which is dense and meter-valued but not calibrated to the sensor or laser-reference geometry. The proposed method constructs a per-pixel depth supervision target by inverse-variance fusion of the sensor depth and the monocular depth prediction. The fused target is used to train a depth-supervised 3D Gaussian Splatting model built on DN-Splatter. Two uncertainty models are evaluated: an implementation-based heuristic, using a configured Kinect noise floor and DA3 depth-structure terms, and a learned-confidence variant, using DA3's native reliability output. The method is evaluated on ten MuSHRoom indoor scenes under held-out Kinect depth metrics, with independent FARO point-cloud and per-frame depth protocols used for additional geometry validation. Across the ten-room MuSHRoom evaluation, heuristic fusion improves RGB quality over sensor-only supervision in all 10 rooms, with mean improvements of 0.42 dB PSNR and 0.009 SSIM and a mean LPIPS reduction of 0.012. Kinect-evaluated geometry stays close to sensor-only supervision with a near-zero median AbsRel increase of 0.0009. FARO-based evaluation supports the same overall geometry conclusion while identifying one point-cloud completeness outlier. The DA3 learned-confidence variant gives mixed appearance changes but consistently worse geometry, showing that a foundation model's internal confidence is not automatically the right uncertainty model for metric fusion. These results support uncertainty-weighted sensor-plus-monocular depth fusion as a practical supervision strategy for indoor 3D Gaussian Splatting."],"dc:identifier":["https://digitalcommons.calpoly.edu/theses/3347"],"dc:subject":["Gaussian Splatting","depth fusion","RGB-D","monocular depth estimation","indoor scene reconstruction"],"dc:title":["Uncertainty-Weighted Fusion of Sensor and Monocular Foundation-Model Depth for 3D Gaussian Splatting in Indoor RGB-D Capture"],"thesis:degree_discipline":["Computer Science"],"thesis:degree_name":["MS in Computer Science"]},"updated_at":"2026-11-19T07:12:58Z"}