SketchBetween: Video-to-Video Synthesis for Sprite Animation via Sketches
Not on the map. Why?
Abstract (arXiv)
2D animation is a common factor in game development, used for characters, effects and background art. It involves work that takes both skill and time, but parts of which are repetitive and tedious. Automated animation approaches exist, but are designed without animators in mind. The focus is heavily on real-life video, which follows strict laws of how objects move, and does not account for the stylistic movement often present in 2D animation. We propose a problem formulation that more closely adheres to the standard workflow of animation. We also demonstrate a model, SketchBetween, which learns to map between keyframes and sketched in-betweens to rendered sprite animations. We demonstrate that our problem formulation provides the required information for the task and that our model outperforms an existing method.
Key facts. Cited by 6 papers in the map (data through 14 Oct 2026). Builds on 21 of its 30 references that are in the map. First posted on arXiv 1 Sep 2022.
Builds on
21 of 30 references.
References · 21
- 2014Adam: A Method for Stochastic Optimizationcited by 37,240
- 2015Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shiftcited by 7,005
- 2017Neural Discrete Representation Learningcited by 4,712
- 2016Image-to-Image Translation with Conditional Adversarial Networkscited by 4,527
- 2021Zero-Shot Text-to-Image Generationcited by 4,288
- 2021GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Modelscited by 3,614
- 2020First Order Motion Model for Image Animationcited by 704
- 2018Video-to-Video Synthesiscited by 390
- 2019Lookahead Optimizer: k steps forward, 1 step backcited by 336
- 2018Animating Arbitrary Objects via Deep Motion Transfercited by 208
- 2019Few-shot Video-to-Video Synthesiscited by 197
- 2018MEMC-Net: Motion Estimation and Motion Compensation Driven Neural Network for Video Interpolation and Enhancementcited by 112
9 more
- 2020Latent Video Transformercited by 106
- 2020World-Consistent Video-to-Video Synthesiscited by 69
- 2019Photo-Sketching: Inferring Contour Drawings from Imagescited by 68
- 2021Deep Animation Video Interpolation in the Wildcited by 65
- 2021Predicting Video with VQVAEcited by 61
- 2020Pose-Guided Human Animation from a Single Image in the Wildcited by 53
- 2020Generating Gameplay-Relevant Art Assets with Transfer Learningcited by 4
- 2022Pixel VQ-VAEs for Improved Pixel Art Representationcited by 4
- 2021Video Frame Interpolation via Structure-Motion based Iterative Fusioncited by 1
Built on by
Citing papers per year: 2024: 1; 2025: 4; 2026: 1.
6 papers.
- 2025Controllable Video Generation: A Surveycited by 98
- 2025Generative AI for Cel-Animation: A Surveycited by 17
- 2025LinkTo-Anime: A 2D Animation Optical Flow Dataset from 3D Model Renderingcited by 2
- 2025DACoN: DINO for Anime Paint Bucket Colorization with Any Number of Reference Imagescited by 2
- 2024A Missing Data Imputation GAN for Character Sprite Generationcited by 0
- 2026SketchKeyAnime: Reference-anchored Sparse Key-Sketch Animation Synthesiscited by 0
- 2026SketchKeyAnime: Reference-anchored Sparse Key-Sketch Animation Synthesis18 Jun 2026
- 2025DACoN: DINO for Anime Paint Bucket Colorization with Any Number of Reference Images18 Sep 2025
- 2025Controllable Video Generation: A Survey22 Jul 2025
- 2025LinkTo-Anime: A 2D Animation Optical Flow Dataset from 3D Model Rendering3 Jun 2025
- 2025Generative AI for Cel-Animation: A Survey8 Jan 2025
- 2024A Missing Data Imputation GAN for Character Sprite Generation16 Sep 2024