AI Paper Atlas

Research map / 3D vision / Face and shape

3D Scene Reconstruction With Multi-Layer Depth and Epipolar Transformers

Daeyun Shin, Zhile Ren, Erik B. Sudderth, Charless C. Fowlkes

ICCV 2019 · 3D vision › Face and shape · approach: Single-view 3D reconstruction · 61 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 overhead EFT height map to first-layer depth D1 (ablation)multi-layer depth model · SUNCG objects (5cm)precision / recall: 0.525 -> 0.553 precision, 0.212 -> 0.275 recallImproved
add overhead EFT height map to four depth layers (ablation)multi-layer depth model · SUNCG objects (5cm)precision / recall: 0.499 -> 0.519 precision, 0.417 -> 0.457 recallImproved
add depth layers 2-4 to the first layer (ablation)multi-layer depth model · SUNCG objects (5cm)precision / recall: 0.525 -> 0.499 precision, 0.212 -> 0.417 recallMixed
add semantic segmentation network features to EFT input (ablation)overhead height map network · SUNCG overhead height mapL1 error: 0.141 -> 0.132Improved
add depth network CNN features rather than only RGB, mask and best guess depth (ablation)overhead height map network · SUNCG overhead height mapL1 error: 0.144 -> 0.132Improved
add back surfaces and more layers (D1..5 vs D1) in ground-truth coverage (ablation)multi-layer depth representation · SUNCG ground-truth coverage (5cm)recall: 0.237 -> 0.924Improved
add overhead virtual view to D1..5 ground-truth layers (ablation)multi-layer depth representation · SUNCG ground-truth coverage (5cm)recall: 0.924 -> 0.932Improved
include back surfaces (layers 1-5 vs 1,3,5 only) in ground truth layers (ablation)multi-layer depth representation · SUNCG scene frustum coveragecoverage: 82% -> 92%Improved
viewer-centered multi-layer + EFT instead of object-based Factored3Dscene reconstruction · ScanNet (1000 images, 10cm)precision / recall: 0.132 -> 0.221 precision, 0.191 -> 0.358 recallImproved
viewer-centered multi-layer + EFT instead of object-based Factored3Dscene reconstruction · SUNCG test objects (voxel IoU)voxel IoU: 0.102 to 0.310Improved

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