# Disentangled Motion Modeling for Video Frame Interpolation

arXiv: https://arxiv.org/abs/2406.17256 · HTML: https://mlsanity.com/paper/2406.17256/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- Builds on 59 of its 74 references that are in the map.
- First posted on arXiv 25 Jun 2024.

## Builds on (most cited first, 30 of 59)

- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [Diffusion Models Beat GANs on Image Synthesis](https://mlsanity.com/paper/2105.05233/) (2021)
- [Deep Unsupervised Learning using Nonequilibrium Thermodynamics](https://mlsanity.com/paper/1503.03585/) (2015)
- [Hierarchical Text-Conditional Image Generation with CLIP Latents](https://mlsanity.com/paper/2204.06125/) (2022)
- [Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding](https://mlsanity.com/paper/2205.11487/) (2022)
- [Taming Transformers for High-Resolution Image Synthesis](https://mlsanity.com/paper/2012.09841/) (2020)
- [Perceptual Losses for Real-Time Style Transfer and Super-Resolution](https://mlsanity.com/paper/1603.08155/) (2016)
- [RAFT: Recurrent All-Pairs Field Transforms for Optical Flow](https://mlsanity.com/paper/2003.12039/) (2020)
- [Video Diffusion Models](https://mlsanity.com/paper/2204.03458/) (2022)
- [Variational Inference with Normalizing Flows](https://mlsanity.com/paper/1505.05770/) (2015)
- [Density estimation using Real NVP](https://mlsanity.com/paper/1605.08803/) (2016)
- [Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network](https://mlsanity.com/paper/1609.04802/) (2016)
- [Imagen Video: High Definition Video Generation with Diffusion Models](https://mlsanity.com/paper/2210.02303/) (2022)
- [Image Super-Resolution via Iterative Refinement](https://mlsanity.com/paper/2104.07636/) (2021)
- [FlowNet: Learning Optical Flow with Convolutional Networks](https://mlsanity.com/paper/1504.06852/) (2015)
- [NICE: Non-linear Independent Components Estimation](https://mlsanity.com/paper/1410.8516/) (2014)
- [PWC-Net: CNNs for Optical Flow Using Pyramid, Warping, and Cost Volume](https://mlsanity.com/paper/1709.02371/) (2017)
- [A Large Dataset to Train Convolutional Networks for Disparity, Optical Flow, and Scene Flow Estimation](https://mlsanity.com/paper/1512.02134/) (2015)
- [Image Quality Assessment: Unifying Structure and Texture Similarity](https://mlsanity.com/paper/2004.07728/) (2020)
- [Video Enhancement with Task-Oriented Flow](https://mlsanity.com/paper/1711.09078/) (2017)
- [PULSE: Self-Supervised Photo Upsampling via Latent Space Exploration of Generative Models](https://mlsanity.com/paper/2003.03808/) (2020)
- [GMFlow: Learning Optical Flow via Global Matching](https://mlsanity.com/paper/2111.13680/) (2021)
- [Super SloMo: High Quality Estimation of Multiple Intermediate Frames for Video Interpolation](https://mlsanity.com/paper/1712.00080/) (2017)
- [MCVD: Masked Conditional Video Diffusion for Prediction, Generation, and Interpolation](https://mlsanity.com/paper/2205.09853/) (2022)
- [Softmax Splatting for Video Frame Interpolation](https://mlsanity.com/paper/2003.05534/) (2020)
- [FlowFormer: A Transformer Architecture for Optical Flow](https://mlsanity.com/paper/2203.16194/) (2022)

## Built on by (most cited first, 11 of 11)

- [MoAlign: Motion-Centric Representation Alignment for Video Diffusion Models](https://mlsanity.com/paper/2510.19022/) (2025)
- [VidTwin: Video VAE with Decoupled Structure and Dynamics](https://mlsanity.com/paper/2412.17726/) (2024)
- [BulletTime: Decoupled Control of Time and Camera Pose for Video Generation](https://mlsanity.com/paper/2512.05076/) (2025)
- [Chain of World: World Model Thinking in Latent Motion](https://mlsanity.com/paper/2603.03195/) (2026)
- [AceVFI: A Comprehensive Survey of Advances in Video Frame Interpolation](https://mlsanity.com/paper/2506.01061/) (2025)
- [4DSloMo: 4D Reconstruction for High Speed Scene with Asynchronous Capture](https://mlsanity.com/paper/2507.05163/) (2025)
- [LumosFlow: Motion-Guided Long Video Generation](https://mlsanity.com/paper/2506.02497/) (2025)
- [MiVID: Multi-Strategic Self-Supervision for Video Frame Interpolation using Diffusion Model](https://mlsanity.com/paper/2511.06019/) (2025)
- [GeoDiffMM: Geometry-Guided Conditional Diffusion for Motion Magnification](https://mlsanity.com/paper/2512.08325/) (2025)
- [DiffST: Spatiotemporal-Aware Diffusion for Real-World Space-Time Video Super-Resolution](https://mlsanity.com/paper/2605.13182/) (2026)
- [TVRN: Invertible Neural Networks for Compression-Aware Temporal Video Rescaling](https://mlsanity.com/paper/2605.15579/) (2026)

## Abstract (arXiv)

Video Frame Interpolation (VFI) aims to synthesize intermediate frames between existing frames to enhance visual smoothness and quality. Beyond the conventional methods based on the reconstruction loss, recent works have employed generative models for improved perceptual quality. However, they require complex training and large computational costs for pixel space modeling. In this paper, we introduce disentangled Motion Modeling (MoMo), a diffusion-based approach for VFI that enhances visual quality by focusing on intermediate motion modeling. We propose a disentangled two-stage training process. In the initial stage, frame synthesis and flow models are trained to generate accurate frames and flows optimal for synthesis. In the subsequent stage, we introduce a motion diffusion model, which incorporates our novel U-Net architecture specifically designed for optical flow, to generate bi-directional flows between frames. By learning the simpler low-frequency representation of motions, MoMo achieves superior perceptual quality with reduced computational demands compared to the generative modeling methods on the pixel space. MoMo surpasses state-of-the-art methods in perceptual metrics across various benchmarks, demonstrating its efficacy and efficiency in VFI.