AI Paper Atlas

Research map / Image generation / Autoregressive and latent generation

Multi-View Data Generation Without View Supervision

Mickael Chen, Ludovic Denoyer, Thierry Artières

ICLR 2018 · Image generation › Autoregressive and latent generation · approach: Generative latent space tooling · 9 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 pair-based adversarial training with a shared content vector and separate sampled view vectorsGMV · CelebAidentity preservation AUC, generated positive vs generated negative pairs: 72.0 % -> 76.3 %Improved
Use shared content with separately sampled views rather than generating a fixed multi-image bundleGMV vs GANx8 · CelebAidentity preservation AUC, real positive vs generated negative pairs: 13.3% -> 78.7 %Improved
Condition the generator on an encoded input and generate views through C-GMVC-GMV vs CGAN · CelebAblurry-image rate: 99.8 % -> 37.2 %Improved
Use C-GMV instead of CGAN for conditional view generationC-GMV · CelebAunique attribute-combination rate: 9% -> 43%Improved
Use C-GMV instead of Mathieu (2016) (DCGAN)C-GMV · CelebAidentity preservation AUC, input/generated positive vs generated-pair negative: 77.3 % -> 67.2%Hurt
Use C-GMV instead of CGANC-GMV · CelebAidentity preservation AUC, generated positive vs generated negative pairs: 100 % -> 75.1%Mixed
Encode content with C-GMVC-GMV · 3D chairsclassification accuracy: 96.7% -> 93.6%Improved
Generate views from encoded content with C-GMVC-GMV · MVC clothclassification accuracy on generated views: 45.2 % -> 27.1%Hurt
Use GMV rather than GANx2 for multi-view generationGMV · CelebABhattacharyya distance to estimated attribute distribution (D2E): 0.25 -> 0.06Improved
Generate content-view pairs with GMV rather than CGANGMV · CelebAblurry-image rate: 99.8 % -> 28.9%Improved

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