AI Paper Atlas

Research map / 3D vision / 3D generation

Generative View Synthesis: From Single-view Semantics to Novel-view Images

Tewodros Amberbir Habtegebrial, Varun Jampani, Orazio Gallo, Didier Stricker

NeurIPS 2020 · 3D vision › 3D generation · approach: Learning 3D reconstruction from images · 4 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 GVSNet's lifted layered semantics and appearance translation rather than the strongest SPADE-plus-NVS baselineGVSNet · CARLAClass Accuracy: 69.93 -> 74.34Improved
Use GVSNet rather than the strongest SPADE-plus-NVS baselineGVSNet · Virtual-KITTI-2Class Accuracy: 76.81 -> 77.13Improved
Use GVSNet rather than the strongest SPADE-plus-NVS baselineGVSNet · CityscapesFID: 57.15 -> 48.72Improved
Add layered, view-independent appearance translation rather than independently translating projected semantics with SPADE (ablation)GVSNet · CARLAFID: 68.96 -> 62.06Improved
Add the Appearance Decoder Network to decode projected high-dimensional appearance features (ablation)SUN + LTN · CARLAFID: 69.46 -> 62.06Improved
Add the Appearance Decoder Network to decode projected high-dimensional appearance features (ablation)SUN + LTN · CARLAClass Accuracy: 71.90 -> 74.34Improved

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