Introduction
DragGAN uses a GAN's feature space for point-based manipulation, demonstrating direct interaction with a generative image manifold. Although diffusion becomes increasingly prominent, this approach remains relevant to the development of editing interfaces in which users move elements visually instead of specifying every change through text.
View full image ↗Page 1 of the linked paper PDF, preserving its original figures and language. The source file identifies the edition; later revision or reprint dates do not replace the node’s historical date.
Xingang Pan et al.; Max Planck Institute for Informatics / Saarland research team · original paper · Image rights remain with their respective holders; no open licence is asserted
Source · Drag Your GAN: Interactive Point-based Manipulation on the Generative Image Manifold ↗RESEARCH ACCOUNT
Editing a generated image by dragging control points.
ANTI-AI ARCHIVE · Revised 2026-10-02
Method and contribution
DragGAN translates user-defined handle and target points into adjustments on a GAN’s image manifold, using feature supervision and point tracking. Demonstrations cover pose, shape, expression and layout; inversion extends the procedure to real images. Reconstructed occluded regions come from the generator, not from visible information already present in the photograph.
Section sources: Drag Your GAN: Interactive Point-based Manipulation on the Generative Image Manifold
Art-historical interpretation
Control shifts from verbal instructions towards direct manipulation, closer to gestures familiar from graphics software. Dragging is not a neutral geometric displacement, however: the model constructs additional structure. Documentation should distinguish observed content from inferred content.
Section sources: Drag Your GAN: Interactive Point-based Manipulation on the Generative Image Manifold
Sources for this account
Author or conference abstract and version record read; full proofs and experiments were not independently reproduced.
This account expands the archive within the cited scope. Historical interpretation is not presented as the original author’s statement or as a proven causal influence. The account and translation are AI-assisted, pending independent human review. Section references identify evidence without claiming independent verification of every historical statement.
Continue with a comparative question
Compare the methods, forms of control or presentation contexts of this entry and StyleGAN.
Compare the methods, forms of control or presentation contexts of this entry and Analyzing and Improving the Image Quality of StyleGAN.
Dates & version record
Date displayed for this node: 2023-05 · Historical date recorded for the source: 2023-05
These dates refer to the historical event or recorded version, not this page’s publication date. The original date precision and unresolved questions are retained.
Original sources & further reading
These links lead to the cited paper, article, institution or conference page. External texts retain their source languages.
Drag Your GAN: Interactive Point-based Manipulation on the Generative Image Manifold
https://arxiv.org/abs/2305.10973
Current cited URL
Provenance, translation & verification
Timeline entry #194 · Historical node
Research materials & supplement references · 2
AI Art Genealogy Research Master · p. 30 · 100
Date as recorded: 2023-05
Drag Your GAN: Interactive Point-based Manipulation on the Generative Image Manifold ↗
Drag Your GAN: Interactive Point-based Manipulation on the Generative Image Manifold
GenAI Visual Release Chronology Research Master · p. 14 · R066
Date as recorded: 2023-05
Drag Your GAN: Interactive Point-based Manipulation on the Generative Image Manifold ↗
Pan et al. — DragGAN
Archive account based on the listed research materials, not a full translation of the linked work. AI-assisted translation; independent human review pending.
The master’s research claims and dates await independent verification.
Cite this node
ANTI-AI ARCHIVE. Drag Your GAN: Interactive Point-based Manipulation on the Generative Image Manifold. Art-history node #194. https://salondesrefuses.cn/en/art-history/100
For specific historical claims, also cite the original sources above and include your access date. This account is not a full translation of the linked work.
Adjacent nodes follow chronological order; adjacency does not establish direct influence or causation.