AI Paper Atlas

Research map / Image generation / Autoregressive and latent generation

Where Is My Spot? Few-Shot Image Generation via Latent Subspace Optimization

Chenxi Zheng, Bangzhen Liu, Huaidong Zhang, Xuemiao Xu, Shengfeng He

CVPR 2023 · Image generation › Autoregressive and latent generation · approach: Generative latent space tooling · 24 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 latent subspace refinement (LSR) to the framework (ablation)latent subspace optimization · Flowers, 3-shotFID: 37.94 -> 34.59 (w/o LSR vs full)Improved
add latent anchor localization (LAL) (ablation)latent subspace optimization · Flowers, 3-shotFID: 36.22 -> 34.59 (w/o LAL vs full)Improved
add latent anchor localization (LAL) (ablation)latent subspace optimization · Flowers, 3-shotLPIPS (diversity): 0.3884 (w/o LAL) -> 0.3914 full is not lower; LAL limits diversity per textHurt
add regularization with seen semantics (ablation)latent subspace optimization · Flowers, 3-shotFID: 53.13 -> 34.59 (w/o Reg vs full)Improved
add latent subspace refinement (LSR) (ablation)latent subspace optimization · Flowers, 3-shottime cost (s): 11 s (w/o LSR) -> 136 s fullHurt
latent subspace optimization vs. prior methods (one-shot)conditional StyleGAN · Flowers / AnimalFaces / VGGFaces, 1-shotFID: FID reduced by 7.58 (Flowers) and 4.37 (AnimalFaces) vs. best baseline; 0.98 on VGGFaces at 3-shotImproved
latent subspace optimization vs. prior methods (3-shot)conditional StyleGAN · Flowers / AnimalFaces / VGGFaces, 3-shotLPIPS (diversity): Flowers 0.3914 vs WaveGAN 0.3868; VGGFaces 0.3344 vs LoFGAN 0.2869 but below AGE/WaveGAN 1-shotMixed
add perceptual/semantic stabilization loss on anchorslatent subspace refinement · qualitativesemantic preservationImproved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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