# High-Resolution Frame Interpolation with Patch-based Cascaded Diffusion

arXiv: https://arxiv.org/abs/2410.11838 · HTML: https://mlsanity.com/paper/2410.11838/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Placed in Diffusion foundations and sampling, one of 14 directions in Diffusion models.
- Builds on 35 of its 49 references that are in the map.
- First posted on arXiv 15 Oct 2024.

## Placed in

- Diffusion models / [Diffusion foundations and sampling](https://mlsanity.com/diffusion/diffusion-foundations-and-sampling/)

## Builds on (most cited first, 30 of 35)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding](https://mlsanity.com/paper/2205.11487/) (2022)
- [RAFT: Recurrent All-Pairs Field Transforms for Optical Flow](https://mlsanity.com/paper/2003.12039/) (2020)
- [Cascaded Diffusion Models for High Fidelity Image Generation](https://mlsanity.com/paper/2106.15282/) (2021)
- [PWC-Net: CNNs for Optical Flow Using Pyramid, Warping, and Cost Volume](https://mlsanity.com/paper/1709.02371/) (2017)
- [MVDream: Multi-view Diffusion for 3D Generation](https://mlsanity.com/paper/2308.16512/) (2023)
- [FlowNet 2.0: Evolution of Optical Flow Estimation with Deep Networks](https://mlsanity.com/paper/1612.01925/) (2016)
- [SyncDreamer: Generating Multiview-consistent Images from a Single-view Image](https://mlsanity.com/paper/2309.03453/) (2023)
- [Video Enhancement with Task-Oriented Flow](https://mlsanity.com/paper/1711.09078/) (2017)
- [MultiDiffusion: Fusing Diffusion Paths for Controlled Image Generation](https://mlsanity.com/paper/2302.08113/) (2023)
- [Label-Efficient Semantic Segmentation with Diffusion Models](https://mlsanity.com/paper/2112.03126/) (2021)
- [Optical Flow Estimation using a Spatial Pyramid Network](https://mlsanity.com/paper/1611.00850/) (2016)
- [Super SloMo: High Quality Estimation of Multiple Intermediate Frames for Video Interpolation](https://mlsanity.com/paper/1712.00080/) (2017)
- [Preserve Your Own Correlation: A Noise Prior for Video Diffusion Models](https://mlsanity.com/paper/2305.10474/) (2023)
- [Softmax Splatting for Video Frame Interpolation](https://mlsanity.com/paper/2003.05534/) (2020)
- [Video Frame Interpolation via Adaptive Separable Convolution](https://mlsanity.com/paper/1708.01692/) (2017)
- [AMT: All-Pairs Multi-Field Transforms for Efficient Frame Interpolation](https://mlsanity.com/paper/2304.09790/) (2023)
- [Video Frame Interpolation via Adaptive Convolution](https://mlsanity.com/paper/1703.07514/) (2017)
- [Context-aware Synthesis for Video Frame Interpolation](https://mlsanity.com/paper/1803.10967/) (2018)
- [FILM: Frame Interpolation for Large Motion](https://mlsanity.com/paper/2202.04901/) (2022)
- [AdaCoF: Adaptive Collaboration of Flows for Video Frame Interpolation](https://mlsanity.com/paper/1907.10244/) (2019)
- [XVFI: eXtreme Video Frame Interpolation](https://mlsanity.com/paper/2103.16206/) (2021)
- [BMBC:Bilateral Motion Estimation with Bilateral Cost Volume for Video Interpolation](https://mlsanity.com/paper/2007.12622/) (2020)
- [Asymmetric Bilateral Motion Estimation for Video Frame Interpolation](https://mlsanity.com/paper/2108.06815/) (2021)
- [FLAVR: Flow-Agnostic Video Representations for Fast Frame Interpolation](https://mlsanity.com/paper/2012.08512/) (2020)
- [PhaseNet for Video Frame Interpolation](https://mlsanity.com/paper/1804.00884/) (2018)
- [Zero-Shot Contrastive Loss for Text-Guided Diffusion Image Style Transfer](https://mlsanity.com/paper/2303.08622/) (2023)
- [Patched Denoising Diffusion Models For High-Resolution Image Synthesis](https://mlsanity.com/paper/2308.01316/) (2023)
- [Any-Size-Diffusion: Toward Efficient Text-Driven Synthesis for Any-Size HD Images](https://mlsanity.com/paper/2308.16582/) (2023)
- [DiffuseHigh: Training-free Progressive High-Resolution Image Synthesis through Structure Guidance](https://mlsanity.com/paper/2406.18459/) (2024)

## Built on by (most cited first, 7 of 7)

- [Hume: Introducing System-2 Thinking in Visual-Language-Action Model](https://mlsanity.com/paper/2505.21432/) (2025)
- [AceVFI: A Comprehensive Survey of Advances in Video Frame Interpolation](https://mlsanity.com/paper/2506.01061/) (2025)
- [SPEED: One-Step Pixel Diffusion for High-quality Video Frame Interpolation](https://mlsanity.com/paper/2607.15585/) (2026)
- [Semantic Frame Interpolation](https://mlsanity.com/paper/2507.05173/) (2025)
- [Taming Real-World Space-Time Video Super-Resolution with One-Step Diffusion](https://mlsanity.com/paper/2601.20308/) (2026)
- [Imagine How To Change: Explicit Procedure Modeling for Change Captioning](https://mlsanity.com/paper/2603.05969/) (2026)
- [P-PatchDiff: Progressive Patch Diffusion Models for Low-light Image Enhancement](https://mlsanity.com/paper/2609.01123/) (2026)

## Abstract (arXiv)

Despite the recent progress, existing frame interpolation methods still struggle with processing extremely high resolution input and handling challenging cases such as repetitive textures, thin objects, and large motion. To address these issues, we introduce a patch-based cascaded pixel diffusion model for high resolution frame interpolation, HiFI, that excels in these scenarios while achieving competitive performance on standard benchmarks. Cascades, which generate a series of images from low to high resolution, can help significantly with large or complex motion that require both global context for a coarse solution and detailed context for high resolution output. However, contrary to prior work on cascaded diffusion models which perform diffusion on increasingly large resolutions, we use a single model that always performs diffusion at the same resolution and upsamples by processing patches of the inputs and the prior solution. At inference time, this drastically reduces memory usage and allows a single model, solving both frame interpolation (base model's task) and spatial up-sampling, saving training cost as well. HiFI excels at high-resolution images and complex repeated textures that require global context, achieving comparable or state-of-the-art performance on various benchmarks (Vimeo, Xiph, X-Test, and SEPE-8K). We further introduce a new dataset, LaMoR, that focuses on particularly challenging cases, and HiFI significantly outperforms other baselines. Please visit our project page for video results: https://hifi-diffusion.github.io