mlsanityData to 7 Oct 2026

Efficient Scale-Invariant Generator with Column-Row Entangled Pixel Synthesis

arXiv 2303.14157 ↗First posted 24 Mar 2023cs.CV cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

Any-scale image synthesis offers an efficient and scalable solution to synthesize photo-realistic images at any scale, even going beyond 2K resolution. However, existing GAN-based solutions depend excessively on convolutions and a hierarchical architecture, which introduce inconsistency and the ``texture sticking" issue when scaling the output resolution. From another perspective, INR-based generators are scale-equivariant by design, but their huge memory footprint and slow inference hinder these networks from being adopted in large-scale or real-time systems. In this work, we propose Column-Row Entangled Pixel Synthesis (CREPS), a new generative model that is both efficient and scale-equivariant without using any spatial convolutions or coarse-to-fine design. To save memory footprint and make the system scalable, we employ a novel bi-line representation that decomposes layer-wise feature maps into separate ``thick" column and row encodings. Experiments on various datasets, including FFHQ, LSUN-Church, MetFaces, and Flickr-Scenery, confirm CREPS' ability to synthesize scale-consistent and alias-free images at any arbitrary resolution with proper training and inference speed. Code is available at https://github.com/VinAIResearch/CREPS.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 27 of its 29 references that are in the map. First posted on arXiv 24 Mar 2023.

Builds on

27 of 29 references.

References · 27

  1. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  2. 2020Denoising Diffusion Implicit Modelscited by 9,655
  3. 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 5,986
  4. 2022Generative Adversarial Networkscited by 5,603
  5. 2019Analyzing and Improving the Image Quality of StyleGANcited by 3,580
  6. 2018Large Scale GAN Training for High Fidelity Natural Image Synthesiscited by 2,609
  7. 2020Implicit Neural Representations with Periodic Activation Functionscited by 2,214
  8. 2020Fourier Features Let Networks Learn High Frequency Functions in Low Dimensional Domainscited by 2,170
  9. 2015Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networkscited by 2,048
  10. 2021Efficient Geometry-aware 3D Generative Adversarial Networkscited by 1,204
  11. 2020Training Generative Adversarial Networks with Limited Datacited by 1,184
  12. 2021Alias-Free Generative Adversarial Networkscited by 1,181
15 more
  1. 2020pi-GAN: Periodic Implicit Generative Adversarial Networks for 3D-Aware Image Synthesiscited by 708
  2. 2020GRAF: Generative Radiance Fields for 3D-Aware Image Synthesiscited by 688
  3. 2021StyleNeRF: A Style-based 3D-Aware Generator for High-resolution Image Synthesiscited by 477
  4. 2021GAN Inversion: A Surveycited by 366
  5. 2021Advances in Neural Renderingcited by 365
  6. 2021StyleSDF: High-Resolution 3D-Consistent Image and Geometry Generationcited by 289
  7. 2020Adversarial Generation of Continuous Imagescited by 135
  8. 2020Image Generators with Conditionally-Independent Pixel Synthesiscited by 105
  9. 2022Any-resolution Training for High-resolution Image Synthesiscited by 72
  10. 2020Positional Encoding as Spatial Inductive Bias in GANscited by 69
  11. 2021In&Out : Diverse Image Outpainting via GAN Inversioncited by 55
  12. 2021Anycost GANs for Interactive Image Synthesis and Editingcited by 54
  13. 2022State-of-the-Art in the Architecture, Methods and Applications of StyleGANcited by 34
  14. 2022Arbitrary-Scale Image Synthesiscited by 20
  15. 2019MSG-GAN: Multi-Scale Gradients for Generative Adversarial Networkscited by 14

Built on by

Not cited yet.