AI Paper Atlas

Research map / Point clouds / Shape and surface completion

Sketch2Vox: Learning 3D Reconstruction from a Single Monocular Sketch Image

Fei Wang

ECCV 2024 · Point clouds › Shape and surface completion · approach: Unsupervised shape correspondence

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 SktMPFM point-cloud branch alongside pixel features (ablation)Sketch2Vox · Sketch3DIoU (average): 0.3354 -> 0.4301Improved
add SktConv pixel branch alongside point features (ablation)Sketch2Vox · Sketch3DIoU (average): 0.4037 -> 0.4301Improved
add CFAM attention fusion instead of direct concatenation (ablation)Sketch2Vox · Sketch3DIoU (average): 0.4045 -> 0.4301Improved
add 3D-Refiner after the decoder (ablation)Sketch2Vox · Sketch3DIoU (average): 0.3775 -> 0.4301Improved
add SktConv pixel branch (ablation)Sketch2Vox · ModelNet synthetic sketchesIoU (average): 0.3262 -> 0.3698Improved
Sketch2Vox versus 3D-R2N2 on precise Canny contoursSketch2Vox · ModelNet synthetic sketchesIoU: 0.3611 -> 0.3698 overallMixed

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