AI Paper Atlas

Research map / 3D vision / Face and shape

SDFusion: Multimodal 3D Shape Completion, Reconstruction, and Generation

CVPR 2023 · 3D vision › Face and shape · approach: 3D shape generative modeling · 201 citations (OpenAlex)

Read the paperCheck your idea against 108,967 papers

AI-extracted summary. Written by AI from the paper's title only (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 latent diffusion over compressed SDFs instead of AutoSDFShape completion on ShapeNet · ShapeNetTMD: 0.0341 -> 0.0885Helped
Use latent diffusion over compressed SDFs instead of AutoSDFShape completion on BuildingNet · BuildingNetTMD: 0.0649 -> 0.0745Helped
Use latent diffusion over compressed SDFs instead of AutoSDFShape completion on ShapeNet · ShapeNetUHD: 0.0567 -> 0.0557Helped
Use latent diffusion over compressed SDFs instead of AutoSDFShape completion on BuildingNet · BuildingNetUHD: 0.1208 -> 0.1116Helped
Use latent diffusion over compressed SDFs instead of AutoSDFSingle-view 3D reconstruction · Pix3DCD: 2.267 -> 1.852Helped
Use latent diffusion over compressed SDFs instead of AutoSDFSingle-view 3D reconstruction · Pix3DF-Score@1%: 0.415 -> 0.432Helped
Use latent diffusion over compressed SDFs instead of AutoSDFText-guided 3D generation · ShapeGlotTarget preference rate: 30% -> 33%Helped

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