# MoSt-DSA: Modeling Motion and Structural Interactions for Direct Multi-Frame Interpolation in DSA Images

arXiv: https://arxiv.org/abs/2407.07078 · HTML: https://mlsanity.com/paper/2407.07078/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 29 of its 38 references that are in the map.
- First posted on arXiv 9 Jul 2024.

## Builds on (most cited first, 29 of 29)

- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [SGDR: Stochastic Gradient Descent with Warm Restarts](https://mlsanity.com/paper/1608.03983/) (2016)
- [Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification](https://mlsanity.com/paper/1502.01852/) (2015)
- [DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs](https://mlsanity.com/paper/1606.00915/) (2016)
- [Real-Time Single Image and Video Super-Resolution Using an Efficient Sub-Pixel Convolutional Neural Network](https://mlsanity.com/paper/1609.05158/) (2016)
- [Video Enhancement with Task-Oriented Flow](https://mlsanity.com/paper/1711.09078/) (2017)
- [Image Inpainting for Irregular Holes Using Partial Convolutions](https://mlsanity.com/paper/1804.07723/) (2018)
- [Super SloMo: High Quality Estimation of Multiple Intermediate Frames for Video Interpolation](https://mlsanity.com/paper/1712.00080/) (2017)
- [Softmax Splatting for Video Frame Interpolation](https://mlsanity.com/paper/2003.05534/) (2020)
- [Depth-Aware Video Frame Interpolation](https://mlsanity.com/paper/1904.00830/) (2019)
- [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)
- [XVFI: eXtreme Video Frame Interpolation](https://mlsanity.com/paper/2103.16206/) (2021)
- [Video Frame Interpolation Transformer](https://mlsanity.com/paper/2111.13817/) (2021)
- [IFRNet: Intermediate Feature Refine Network for Efficient Frame Interpolation](https://mlsanity.com/paper/2205.14620/) (2022)
- [LambdaNetworks: Modeling Long-Range Interactions Without Attention](https://mlsanity.com/paper/2102.08602/) (2021)
- [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)
- [Extracting Motion and Appearance via Inter-Frame Attention for Efficient Video Frame Interpolation](https://mlsanity.com/paper/2303.00440/) (2023)
- [CDFI: Compression-Driven Network Design for Frame Interpolation](https://mlsanity.com/paper/2103.10559/) (2021)
- [SDCNet: Video Prediction Using Spatially-Displaced Convolution](https://mlsanity.com/paper/1811.00684/) (2018)
- [A Unified Pyramid Recurrent Network for Video Frame Interpolation](https://mlsanity.com/paper/2211.03456/) (2022)
- [ST-MFNet: A Spatio-Temporal Multi-Flow Network for Frame Interpolation](https://mlsanity.com/paper/2111.15483/) (2021)
- [A Spatiotemporal Volumetric Interpolation Network for 4D Dynamic Medical Image](https://mlsanity.com/paper/2002.12680/) (2020)
- [Joint Video Multi-Frame Interpolation and Deblurring under Unknown Exposure Time](https://mlsanity.com/paper/2303.15043/) (2023)
- [Neighbor Correspondence Matching for Flow-based Video Frame Synthesis](https://mlsanity.com/paper/2207.06763/) (2022)
- [Video Frame Interpolation with Densely Queried Bilateral Correlation](https://mlsanity.com/paper/2304.13596/) (2023)
- [Video Frame Interpolation with Flow Transformer](https://mlsanity.com/paper/2307.16144/) (2023)

## Built on by (most cited first, 4 of 4)

- [GaraMoSt: Parallel Multi-Granularity Motion and Structural Modeling for Efficient Multi-Frame Interpolation in DSA Images](https://mlsanity.com/paper/2412.14118/) (2024)
- [UniX: Unifying Autoregression and Diffusion for Chest X-Ray Understanding and Generation](https://mlsanity.com/paper/2601.11522/) (2026)
- [DSA-SRGS: Super-Resolution Gaussian Splatting for Dynamic Sparse-View DSA Reconstruction](https://mlsanity.com/paper/2603.04770/) (2026)
- [Moebius: 0.2B Lightweight Image Inpainting Framework with 10B-Level Performance](https://mlsanity.com/paper/2606.19195/) (2026)

## Abstract (arXiv)

Artificial intelligence has become a crucial tool for medical image analysis. As an advanced cerebral angiography technique, Digital Subtraction Angiography (DSA) poses a challenge where the radiation dose to humans is proportional to the image count. By reducing images and using AI interpolation instead, the radiation can be cut significantly. However, DSA images present more complex motion and structural features than natural scenes, making interpolation more challenging. We propose MoSt-DSA, the first work that uses deep learning for DSA frame interpolation. Unlike natural scene Video Frame Interpolation (VFI) methods that extract unclear or coarse-grained features, we devise a general module that models motion and structural context interactions between frames in an efficient full convolution manner by adjusting optimal context range and transforming contexts into linear functions. Benefiting from this, MoSt-DSA is also the first method that directly achieves any number of interpolations at any time steps with just one forward pass during both training and testing. We conduct extensive comparisons with 7 representative VFI models for interpolating 1 to 3 frames, MoSt-DSA demonstrates robust results across 470 DSA image sequences (each typically 152 images), with average SSIM over 0.93, average PSNR over 38 (standard deviations of less than 0.030 and 3.6, respectively), comprehensively achieving state-of-the-art performance in accuracy, speed, visual effect, and memory usage. Our code is available at https://github.com/ZyoungXu/MoSt-DSA.