AI Paper Atlas

Research map / 3D vision / Face and shape

Learning Priors for Semantic 3D Reconstruction

Ian Cherabier, Johannes L. Schonberger, Martin R. Oswald, Marc Pollefeys, Andreas Geiger

ECCV 2018 · 3D vision › Face and shape · approach: Learned mesh and geometric representations · 48 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 unrolled variational regularization (50 iterations) to the network (ablation)Ours-300 · ScanNet (156 test scenes, weak data cost)overall accuracy: 97.3 -> 98.7Improved
add unrolled variational regularization (50 iterations) to the network (ablation)Ours-300 · ScanNet (156 test scenes, weak data cost)freespace accuracy: 97.6 -> 98.6Improved
add unrolled variational regularization (50 iterations) to the network (ablation)Ours-300 · ScanNet (156 test scenes, weak data cost)occupied accuracy: 92.3 -> 94.4Improved
add unrolled variational regularization (50 iterations) to the network (ablation)Ours-300 · ScanNet (156 test scenes, weak data cost)semantic accuracy: 90.2 -> 91.5Improved
train on 312 scenes instead of only 5 scenes (ablation)Ours · ScanNet (156 test scenes, weak data cost)overall accuracy: 96.7 -> 98.7Improved
use learned multi-scale network instead of TV-L1 at 50 iterationsOurs · ScanNet (156 test scenes, weak data cost)overall accuracy: 92.8 -> 98.7Improved
use learned network (50 it.) instead of TV-L1 run to convergence (500 it.)Ours · ScanNet (156 test scenes, weak data cost)overall accuracy: 95.8 -> 98.7Improved
use multi-scale architecture instead of naive coarse-to-fine network (ablation)Ours · ScanNet (156 test scenes, weak data cost)overall accuracy: 21.0 -> 98.7Improved
add multi-scale (3 levels) to the unrolled network (ablation)Ours-300 · ScanNet (156 test scenes, weak data cost)overall accuracy: 98.7 -> 98.7No clear effect
increase TV-L1 iterations from 50 to 500TV-L1 · ScanNet (156 test scenes, weak data cost)overall accuracy: 92.8 -> 95.8Improved
replace Wulffshape hand-crafted regularizer with learned priorsHaene et al. [12] · Haene et al. outdoor scenes (Castle, South Building)iterations: 2750 -> 50Improved

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