AI Paper Atlas

Research map / 3D vision / 3D generation

ForkNet: Multi-Branch Volumetric Semantic Completion From a Single Depth Image

Yida Wang, David Joseph Tan, Nassir Navab, Federico Tombari

ICCV 2019 · 3D vision › 3D generation · approach: Semantic scene completion · 69 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 SDF-semantic consistency loss with latent-sampled pairs (ablation)ForkNet · SUNCG semantic scene completionaverage IoU (%): 58.2 -> 63.4Improved
add geometric completion branch (ablation)ForkNet · SUNCG semantic scene completionaverage IoU (%): 62.3 -> 63.4Improved
add SDF-semantic consistency loss with latent-sampled pairs (ablation)ForkNet · NYU semantic scene completionaverage IoU (%): 34.7 -> 37.1Improved
add geometric completion branch (ablation)ForkNet · NYU semantic scene completionaverage IoU (%): 36.5 -> 37.1Improved
add SDF-semantic consistency loss with latent-sampled pairs (ablation)ForkNet · SUNCG scene completionIoU (%): 82.0 -> 86.9Improved
add geometric completion branch (ablation)ForkNet · SUNCG scene completionIoU (%): 82.3 -> 86.9Improved
add SDF-semantic consistency loss with latent-sampled pairs (ablation)ForkNet · NYU scene completionIoU (%): 61.1 -> 63.4Improved
add geometric completion branch (ablation)ForkNet · NYU scene completionIoU (%): 62.6 -> 63.4Improved
add SDF-semantic consistency loss with latent-sampled pairs (ablation)ForkNet · ShapeNet object completion (single category)average IoU (%): 80.4 -> 84.1Improved
add SDF-semantic consistency loss with latent-sampled pairs (ablation)ForkNet · 3D-RecGAN real-world object completionaverage IoU (%): 20.3 -> 23.8Improved
ForkNet vs VVNet on SUNCG full-volume semantic completionForkNet · SUNCG semantic scene completionaverage IoU (%): 66.7 vs 63.4Hurt
ForkNet vs SaTNet on NYU semantic completionForkNet · NYU semantic scene completionaverage IoU (%): 34.4 -> 37.1Improved

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