AI Paper Atlas

Research map / 3D vision / 3D generation

Semantically Informed Multiview Surface Refinement

Maros Blaha, Mathias Rothermel, Martin R. Oswald, Torsten Sattler, Audrey Richard, Jan D. Wegner, Marc Pollefeys, Konrad Schindler

ICCV 2017 · 3D vision › 3D generation · approach: Semantic scene completion · 36 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add semantic label consistency and class-specific shape priors to geometric mesh refinementmesh refinement from semantic 3D reconstruction input · SynthCity3 Amean distance to ground truth (m): 0.44 -> 0.38Improved
add semantic label consistency and class-specific shape priors to geometric mesh refinementmesh refinement from semantic 3D reconstruction input · SynthCity3 Bmean distance to ground truth (m): 0.74 -> 0.62Improved
add semantic relabeling with shape priors to geometric refinementmesh refinement from semantic 3D reconstruction input · SynthCity3 Asemantic average accuracy (%): 82.8 -> 88.8Improved
add semantic relabeling with shape priors to geometric refinementmesh refinement from semantic 3D reconstruction input · SynthCity3 Bsemantic average accuracy (%): 83.8 -> 90.0Improved
add semantic relabeling with shape priors to geometric refinementmesh refinement from semantic 3D reconstruction input · Enschede Asemantic average accuracy (%): 78.8 -> 83.3Improved
add semantic relabeling with shape priors to geometric refinementmesh refinement from semantic 3D reconstruction input · Enschede Bsemantic overall accuracy (%): 90.6 -> 94.1Improved
add semantic relabeling with shape priors to geometric refinementmesh refinement from semantic 3D reconstruction input · Dortmundsemantic average accuracy (%): 86.6 -> 87.6Improved
add semantic relabeling with shape priors to geometric refinementmesh refinement from semantic 3D reconstruction input · Dortmundsemantic overall accuracy (%): 92.4 -> 92.7No clear effect
add semantic relabeling with shape priors to geometric refinementmesh refinement from semantic 3D reconstruction input · Southbuilding (terrestrial)semantic average accuracy (%): 78.7 -> 94.5Improved
add semantic relabeling with shape priors to geometric refinementmesh refinement from semantic 3D reconstruction input · Southbuilding (terrestrial)semantic overall accuracy (%): 93.8 -> 98.0Improved
apply purely geometric baseline refinement to the semantic 3D reconstruction inputmesh refinement from semantic 3D reconstruction input · SynthCity3 Amean distance to ground truth (m): 0.52 -> 0.44Improved
apply purely geometric baseline refinement to the semantic 3D reconstruction inputmesh refinement from semantic 3D reconstruction input · Southbuilding (terrestrial)semantic average accuracy (%): 81.9 -> 78.7Hurt

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy