AI Paper Atlas

Research map / Point clouds / Shape and surface completion

CAPNet: Continuous Approximation Projection for 3D Point Cloud Reconstruction Using 2D Supervision

K. L. Navaneet, Priyanka Mandikal, Mayank Agarwal, R. Venkatesh Babu

AAAI 2019 · Point clouds › Shape and surface completion · approach: Point cloud upsampling and normals · 60 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
Use CAPNet with mask supervision instead of DRC-MaskShapeNet reconstruction · ShapeNet (mean)Chamfer distance (×1000): 13.26 -> 2.69Improved
Use CAPNet with mask supervision instead of Lin et al.ShapeNet reconstruction · ShapeNet (mean)Chamfer distance (×1000): 3.62 -> 2.69Improved
Fine-tune PSGN-FC using 2D mask supervisionPSGN-FC · Pix3D testChamfer distance (×1000): 10.1 -> 9.2Improved
Optimize the encoder while fixing the decoder using the test mask (ablation)Pre-trained PSGN-FC · Test-stage optimizationChamfer distance (×1000): 4.64 -> 4.43Improved
Optimize both encoder and decoder with regularization using the test maskPre-trained PSGN-FC · Test-stage optimizationChamfer distance (×1000): 4.64 -> 4.37Improved
Optimize predicted points directly using the test mask (ablation)Pre-trained PSGN-FC · Test-stage optimizationChamfer distance (×1000): 4.64 -> 4.49Improved
Increase mask supervision from one view to two views (ablation)CAPNet · ShapeNet airplaneChamfer distance (×1000): 2.40 -> 2.02Improved
Increase mask supervision from one view to two views (ablation)CAPNet · ShapeNet carChamfer distance (×1000): 3.47 -> 1.68Improved
Increase mask supervision from one view to two views (ablation)CAPNet · ShapeNet chairChamfer distance (×1000): 4.53 -> 4.41Improved
Add affinity loss to binary cross-entropy mask loss (ablation)CAPNet · ShapeNetChamfer distanceImproved
Use high affinity-loss weight throughout training (ablation)CAPNet · ShapeNet chairreconstruction of thin structuresHurt
Use category-specific kernel variance instead of one multi-category setting (ablation)CAPNet (multi-cat) · ShapeNet airplanebody-shape fidelityImproved

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