Lune

CVPR2021Top-tier venue

Anycost GANs for Interactive Image Synthesis and Editing

Ji Lin, Richard Zhang, Frieder Ganz, Song Han, Jun-Yan Zhu

Abstract

input projected 2x faster 4x faster 8x faster edit: no smile 8x faster edit: hair color 8x faster (a) input images (b) Anycost GANs provide consistent outputs for projected latent code (c) Consistency remains after editing less hair color Figure 1: Anycost GAN can be executed at flexible computation costs (fast preview with low cost and high-quality output with full cost), enabling interactive image editing with quick preview. The low-cost sub-generator produces consistent outputs compared to the full-cost generator during both image projection and latent code traversal, making the sub-generator an accurate proxy for various editing tasks (e.g., no smile, changing hair color). Interactive demos are available here.

Ask Lune

Know this paper in minutes, not an afternoon.

Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.

25 top-tier papers have cited it since. Know what they found before your reviewers do.

Questions to start from

Lune can draw on

the full paper · the top-tier papers that cite it · related work

Get the answer

Free to start. No credit card required.

Lineage

  • MCUNet: Tiny Deep Learning on IoT Devices cites Once-for-All: Train One Network and Specialize it for Efficient Deployment
  • Patch Diffusion: Faster and More Data-Efficient Training of Diffusion Models cites Once-for-All: Train One Network and Specialize it for Efficient Deployment
  • Patch Diffusion: Faster and More Data-Efficient Training of Diffusion Models cites Training Generative Adversarial Networks with Limited Data
  • HyperStyle: StyleGAN Inversion with HyperNetworks for Real Image Editing cites Image2StyleGAN: How to Embed Images Into the StyleGAN Latent Space?
  • HyperStyle: StyleGAN Inversion with HyperNetworks for Real Image Editing cites Training Generative Adversarial Networks with Limited Data
  • The GAN is dead; long live the GAN! A Modern GAN Baseline cites Training Generative Adversarial Networks with Limited Data
  • Efficient Spatially Sparse Inference for Conditional GANs and Diffusion Models cites MCUNet: Tiny Deep Learning on IoT Devices
  • Efficient Spatially Sparse Inference for Conditional GANs and Diffusion Models cites Image2StyleGAN: How to Embed Images Into the StyleGAN Latent Space?
Builds onCited byLeft to right by year; the more cited, the higher.

Cited by top-tier papers25

  1. HyperStyle: StyleGAN Inversion with HyperNetworks for Real Image EditingYuval Alaluf, Omer Tov, Ron Mokady, Rinon Gal et al.CVPR 2022 · 250 citations
  2. Patch Diffusion: Faster and More Data-Efficient Training of Diffusion ModelsZhendong Wang, Yifan Jiang, Huangjie Zheng, Peihao Wang et al.NeurIPS 2023 · 205 citations
  3. The GAN is dead; long live the GAN! A Modern GAN BaselineNick Huang, Aaron Gokaslan, Volodymyr Kuleshov, James TompkinNeurIPS 2024 · 111 citations
  4. Adv-Attribute: Inconspicuous and Transferable Adversarial Attack on Face RecognitionShuai Jia, Bangjie Yin, Taiping Yao, Shouhong Ding et al.NeurIPS 2022 · 84 citations
  5. Efficient Spatially Sparse Inference for Conditional GANs and Diffusion ModelsMuyang Li, Ji Lin, Chenlin Meng, Stefano Ermon et al.NeurIPS 2022 · 66 citations

Builds on19

  1. Training Generative Adversarial Networks with Limited DataTero Karras, Miika Aittala, Janne Hellsten, Samuli Laine et al.NeurIPS 2020 · 2,345 citations
  2. Once-for-All: Train One Network and Specialize it for Efficient DeploymentHan Cai, Chuang Gan, Tianzhe Wang, Zhekai Zhang et al.ICLR 2020 · 1,522 citations
  3. Image2StyleGAN: How to Embed Images Into the StyleGAN Latent Space?Rameen Abdal, Yipeng Qin, Peter WonkaICCV 2019 · 1,195 citations
  4. GANSpace: Discovering Interpretable GAN ControlsErik Härkönen, Aaron Hertzmann, Jaakko Lehtinen, Sylvain ParisNeurIPS 2020 · 1,049 citations
  5. MCUNet: Tiny Deep Learning on IoT DevicesJi Lin, Wei-Ming Chen, Yujun Lin, John Cohn et al.NeurIPS 2020 · 827 citations

Related papers

  1. Surrogate Gradient Field for Latent Space ManipulationMinjun Li, Yanghua Jin, Huachun ZhuCVPR 2021
  2. Using latent space regression to analyze and leverage compositionality in GANsLucy Chai, Jonas Wulff, Phillip IsolaICLR 2021 · 30 citations
  3. GlassesGAN: Eyewear Personalization Using Synthetic Appearance Discovery and Targeted Subspace ModelingRichard Plesh, Peter Peer, Vitomir StrucCVPR 2023
  4. Auto DragGAN: Editing the Generative Image Manifold in an Autoregressive MannerPengxiang Cai, Zhiwei Liu, Guibo Zhu, Yunfang Niu et al.ACM MM 2024 · 3 citations
  5. Where is My Spot? Few-shot Image Generation via Latent Subspace OptimizationChenxi Zheng, Bangzhen Liu, Huaidong Zhang, Xuemiao Xu et al.CVPR 2023
Dusk over the sea between two cliffs drawn in fine vertical lines