AI Paper Atlas

Research map / Image generation / Autoregressive and latent generation

Language-driven Scene Synthesis using Multi-conditional Diffusion Model

An Dinh Vuong, Minh Nhat VU, Toan Tien Nguyen, Baoru Huang, Dzung Nguyen, Thieu Vo, Anh Nguyen

NeurIPS 2023 · Image generation › Autoregressive and latent generation · approach: Compositional scene generation · 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 LSDM instead of MCDM3D scene synthesis · PRO-teXtCD: 0.6301 -> 0.5365Improved
Use LSDM instead of MCDM3D scene synthesis · PRO-teXtF1: 0.3574 -> 0.5160Improved
Use LSDM instead of MCDM3D scene synthesis · HUMANISEF1: 0.2515 -> 0.4395Improved
Add text input (ablation)LSDM · PRO-teXtF1: 0.0506 -> 0.5160Improved
Add high-level translation vectors and guiding points (ablation)LSDM · PRO-teXtF1: 0.0391 -> 0.5160Improved
Use point-wise transformations (ablation)LSDM · PRO-teXtF1: 0.2400 -> 0.5160Improved
Add human input to the objects-only setting (ablation)LSDM · PRO-teXtF1: 0.3185 -> 0.5160Improved
Add existing-object input to the human-only setting (ablation)LSDM · PRO-teXtF1: 0.3855 -> 0.5160Improved

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