AI Paper Atlas

Research map / 3D vision / Face and shape

Convolutional Occupancy Networks

Songyou Peng, Michael Niemeyer, Lars Mescheder, Marc Pollefeys, Andreas Geiger

ECCV 2020 · 3D vision › Face and shape · approach: Learned mesh and geometric representations · 902 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
replace fully-connected ONet encoding with convolutional 3-plane featuresOccupancy Networks · ShapeNet point cloud reconstructionIoU: 0.761 -> 0.884Improved
project features to three canonical planes instead of a single plane (ablation)Ours-2D · ShapeNet point cloud reconstructionIoU: 0.833 -> 0.884Improved
use plane projection plus 2D/3D CNN instead of direct point feature aggregation (PointConv) (ablation)Convolutional Occupancy Networks · ShapeNet point cloud reconstructionIoU: 0.689 -> 0.884Improved
decompose volume into three higher-resolution planes (64^2 vs 32^3) (ablation)Convolutional Occupancy Networks · ShapeNet point cloud reconstructionGPU memory: 5.9G -> 2.4GImproved
use three planes instead of a single plane for coarse voxel input (ablation)Ours-2D · ShapeNet voxel super-resolutionIoU: 0.652 -> 0.752Improved
three planes instead of volume on voxel super-resolution (ablation)Convolutional Occupancy Networks · ShapeNet voxel super-resolutionGPU memory: 10.8G -> 4.0GImproved
combine multi-plane and volume features (ablation)Ours-2D (3x128^2) · Synthetic RoomsIoU: 0.805 -> 0.816Improved
increase volume resolution from 32^3 to 64^3 (ablation)Ours-3D · Synthetic RoomsIoU: 0.782 -> 0.849Improved
use bilinear instead of nearest neighbor interpolation (ablation)Ours-2D (3x128^2) · Synthetic RoomsIoU: 0.766 -> 0.805Improved
use three planes instead of a single higher-resolution plane at similar GPU memory (ablation)Ours-2D · Synthetic RoomsIoU: 0.773 -> 0.805Improved
use volumetric features instead of three-plane features on real data (ablation)Convolutional Occupancy Networks · ScanNet v2F-Score: 0.776 -> 0.837Improved
increase volume resolution from 32^3 to 64^3 on real data (ablation)Ours-3D · ScanNet v2F-Score: 0.837 -> 0.886Improved

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