Pith. sign in

REVIEW 4 cited by

GANSpace: Discovering Interpretable GAN Controls

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2004.02546 v3 pith:F5YPCFIO submitted 2020-04-06 cs.CV cs.GR

Erik Härkönen , Aaron Hertzmann , Jaakko Lehtinen , Sylvain Paris This is my paper · ORCID
classification cs.CVcs.GR
keywords controlsdirectionsinterpretableganslatentlayer-wiseprincipalspace
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original abstract

This paper describes a simple technique to analyze Generative Adversarial Networks (GANs) and create interpretable controls for image synthesis, such as change of viewpoint, aging, lighting, and time of day. We identify important latent directions based on Principal Components Analysis (PCA) applied either in latent space or feature space. Then, we show that a large number of interpretable controls can be defined by layer-wise perturbation along the principal directions. Moreover, we show that BigGAN can be controlled with layer-wise inputs in a StyleGAN-like manner. We show results on different GANs trained on various datasets, and demonstrate good qualitative matches to edit directions found through earlier supervised approaches.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 4 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. TokenVerse: Versatile Multi-concept Personalization in Token Modulation Space

    cs.CV 2025-01 conditional novelty 7.0 of 10

    TokenVerse personalizes multiple visual concepts, including non-object concepts like pose and lighting, by learning per-text-token modulation offsets in a pretrained text-to-image Diffusion Transformer.

  2. XFACTORS: Disentangled Information Bottleneck via Contrastive Supervision

    cs.LG 2026-01 conditional novelty 6.0 of 10

    XFACTORS separates latent factors into per-factor subspaces with InfoNCE supervision, achieving near-perfect FactorVAE scores on synthetic benchmarks and qualitative factor swapping on CelebA.

  3. MyTimeMachine: Personalized Facial Age Transformation

    cs.CV 2024-11 conditional novelty 6.0 of 10

    A personalized facial age transformation method that uses an adapter network on top of the SAM global aging model, trained with 10 to 50 photos of one person, to produce re-aged images that resemble that person's actu...

  4. StyleAutoEncoder for manipulating image attributes using pre-trained StyleGAN

    cs.CV 2024-12 conditional novelty 4.0 of 10

    StyleAE is a lightweight autoencoder attached to StyleGAN that edits image attributes by modifying single coordinates of a learned target latent space, matching or approaching flow-based baselines with far lower cost.

Pith tools