Endless Loops: Detecting and Animating Periodic Patterns in Still Images
Not on the map. Why?
Abstract (arXiv)
We present an algorithm for producing a seamless animated loop from a single image. The algorithm detects periodic structures, such as the windows of a building or the steps of a staircase, and generates a non-trivial displacement vector field that maps each segment of the structure onto a neighboring segment along a user- or auto-selected main direction of motion. This displacement field is used, together with suitable temporal and spatial smoothing, to warp the image and produce the frames of a continuous animation loop. Our cinemagraphs are created in under a second on a mobile device. Over 140,000 users downloaded our app and exported over 350,000 cinemagraphs. Moreover, we conducted two user studies that show that users prefer our method for creating surreal and structured cinemagraphs compared to more manual approaches and compared to previous methods.
Key facts. Cited by 7 papers in the map (data through 7 Oct 2026). Builds on 11 of its 47 references that are in the map. First posted on arXiv 19 May 2021.
Builds on
11 of 47 references.
References · 11
- 2019SinGAN: Learning a Generative Model from a Single Natural Imagecited by 348
- 2020Softmax Splatting for Video Frame Interpolationcited by 276
- 20203D Photography using Context-aware Layered Depth Inpaintingcited by 206
- 20193D Ken Burns Effect from a Single Imagecited by 128
- 2020Learning by Analogy: Reliable Supervision from Transformations for Unsupervised Optical Flow Estimationcited by 120
- 2018Photo Wake-Up: 3D Character Animation from a Single Photocited by 60
- 2020Animating Pictures with Eulerian Motion Fieldscited by 54
- 2020One Shot 3D Photographycited by 45
- 2017Two-Stream Convolutional Networks for Dynamic Texture Synthesiscited by 15
- 2019Animating Landscape: Self-Supervised Learning of Decoupled Motion and Appearance for Single-Image Video Synthesiscited by 15
- 2019Clear Skies Ahead: Towards Real-Time Automatic Sky Replacement in Videocited by 1
Built on by
Citing papers per year: 2022: 2; 2023: 3; 2024: 1; 2025: 1.
7 papers.
- 2023Text-Guided Synthesis of Eulerian Cinemagraphscited by 22
- 2023Blowing in the Wind: CycleNet for Human Cinemagraphs from Still Imagescited by 14
- 2024LoopGaussian: Creating 3D Cinemagraph with Multi-view Images via Eulerian Motion Fieldcited by 8
- 2022Learning Continuous Implicit Representation for Near-Periodic Patternscited by 4
- 20233D Video Loops from Asynchronous Inputcited by 4
- 2025Mobius: Text to Seamless Looping Video Generation via Latent Shiftcited by 3
- 2022Deep Learning and Synthetic Mediacited by 1
- 2025Mobius: Text to Seamless Looping Video Generation via Latent Shift27 Feb 2025
- 2024LoopGaussian: Creating 3D Cinemagraph with Multi-view Images via Eulerian Motion Field13 Apr 2024
- 2023Text-Guided Synthesis of Eulerian Cinemagraphs6 Jul 2023
- 2023Blowing in the Wind: CycleNet for Human Cinemagraphs from Still Images15 Mar 2023
- 20233D Video Loops from Asynchronous Input9 Mar 2023
- 2022Learning Continuous Implicit Representation for Near-Periodic Patterns25 Aug 2022
- 2022Deep Learning and Synthetic Media11 May 2022