Pith. sign in

REVIEW 6 cited by

StyleGAN-XL: Scaling StyleGAN to Large Diverse Datasets

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 2202.00273 v2 pith:B2P5ANX2 submitted 2022-02-01 cs.LG cs.CV

Axel Sauer , Katja Schwarz , Andreas Geiger This is my paper · ORCID
classification cs.LGcs.CV
keywords stylegandatasetscontrollabilitydiverseimageimagenetimageslarge
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
abstract

Computer graphics has experienced a recent surge of data-centric approaches for photorealistic and controllable content creation. StyleGAN in particular sets new standards for generative modeling regarding image quality and controllability. However, StyleGAN's performance severely degrades on large unstructured datasets such as ImageNet. StyleGAN was designed for controllability; hence, prior works suspect its restrictive design to be unsuitable for diverse datasets. In contrast, we find the main limiting factor to be the current training strategy. Following the recently introduced Projected GAN paradigm, we leverage powerful neural network priors and a progressive growing strategy to successfully train the latest StyleGAN3 generator on ImageNet. Our final model, StyleGAN-XL, sets a new state-of-the-art on large-scale image synthesis and is the first to generate images at a resolution of $1024^2$ at such a dataset scale. We demonstrate that this model can invert and edit images beyond the narrow domain of portraits or specific object classes.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 6 Pith papers

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

  1. ROMS-IMLE: A Minimalist Approach to Competitive Single-Step Generative Modelling

    cs.LG 2026-07 conditional novelty 6.0 of 10

    A single-step IMLE generator with per-stage supervision and a robust loss reports FID 2.56 on ImageNet-256 by filtering ~5% of samples at test time.

  2. ELT: Elastic Looped Transformers for Visual Generation

    cs.CV 2026-04 unverdicted novelty 6.0 of 10

    Weight-shared looped transformers trained with intra-loop self-distillation match MaskGIT-class FID/FVD at roughly 4x fewer parameters and support any-time inference across loop counts.

  3. Masked Generative Nested Transformers with Decode Time Scaling

    cs.CV 2025-02 conditional novelty 6.0 of 10

    MaGNeTS schedules progressively larger nested transformer sub-models over decode iterations and caches key-value pairs of unmasked tokens, achieving 2.5-3.7x compute reduction with competitive FID/FVD.

  4. Image Generation Diversity Issues and How to Tame Them

    cs.CV 2024-11 conditional novelty 6.0 of 10

    The paper proposes a retrieval-based diversity metric (IRS), finds that state-of-the-art diffusion models retrieve at most 77% of training images, and introduces feature-conditioned DiADM to improve unconditional diversity.

  5. Enhancing Low-Cost Video Editing with Lightweight Adaptors and Temporal-Aware Inversion

    cs.CV 2025-01 reject novelty 4.0 of 10

    GE-Adapter combines a temporal smoothness loss, bilateral-filtered DDIM inversion, and shared plus frame-specific prompt tokens to improve text-to-video editing, though the reported evidence is inconsistent.

  6. Efficient Temporal Consistency in Diffusion-Based Video Editing with Adaptor Modules: A Theoretical Framework

    cs.CV 2025-04 reject novelty 3.0 of 10

    The paper attempts, but fails, to prove convergence and stability guarantees for adapter-based temporal consistency in diffusion video editing.

Pith tools