# GS-STVSR: Ultra-Efficient Continuous Spatio-Temporal Video Super-Resolution via 2D Gaussian Splatting

arXiv: https://arxiv.org/abs/2604.18047 · HTML: https://mlsanity.com/paper/2604.18047/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 90 of its 141 references that are in the map.
- First posted on arXiv 20 Apr 2026.

## Builds on (most cited first, 30 of 90)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [3D Gaussian Splatting for Real-Time Radiance Field Rendering](https://mlsanity.com/paper/2308.04079/) (2023)
- [RAFT: Recurrent All-Pairs Field Transforms for Optical Flow](https://mlsanity.com/paper/2003.12039/) (2020)
- [Implicit Neural Representations with Periodic Activation Functions](https://mlsanity.com/paper/2006.09661/) (2020)
- [Fourier Features Let Networks Learn High Frequency Functions in Low Dimensional Domains](https://mlsanity.com/paper/2006.10739/) (2020)
- [On the Spectral Bias of Neural Networks](https://mlsanity.com/paper/1806.08734/) (2018)
- [4D Gaussian Splatting for Real-Time Dynamic Scene Rendering](https://mlsanity.com/paper/2310.08528/) (2023)
- [Dynamic 3D Gaussians: Tracking by Persistent Dynamic View Synthesis](https://mlsanity.com/paper/2308.09713/) (2023)
- [Deep Multi-scale Convolutional Neural Network for Dynamic Scene Deblurring](https://mlsanity.com/paper/1612.02177/) (2016)
- [Learning Continuous Image Representation with Local Implicit Image Function](https://mlsanity.com/paper/2012.09161/) (2020)
- [EDVR: Video Restoration with Enhanced Deformable Convolutional Networks](https://mlsanity.com/paper/1905.02716/) (2019)
- [Optical Flow Estimation using a Spatial Pyramid Network](https://mlsanity.com/paper/1611.00850/) (2016)
- [SC-GS: Sparse-Controlled Gaussian Splatting for Editable Dynamic Scenes](https://mlsanity.com/paper/2312.14937/) (2023)
- [Fast Dynamic Radiance Fields with Time-Aware Neural Voxels](https://mlsanity.com/paper/2205.15285/) (2022)
- [Spacetime Gaussian Feature Splatting for Real-Time Dynamic View Synthesis](https://mlsanity.com/paper/2312.16812/) (2023)
- [BasicVSR++: Improving Video Super-Resolution with Enhanced Propagation and Alignment](https://mlsanity.com/paper/2104.13371/) (2021)
- [Super SloMo: High Quality Estimation of Multiple Intermediate Frames for Video Interpolation](https://mlsanity.com/paper/1712.00080/) (2017)
- [MACE: Mass Concept Erasure in Diffusion Models](https://mlsanity.com/paper/2403.06135/) (2024)
- [BasicVSR: The Search for Essential Components in Video Super-Resolution and Beyond](https://mlsanity.com/paper/2012.02181/) (2020)
- [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)
- [TF-ICON: Diffusion-Based Training-Free Cross-Domain Image Composition](https://mlsanity.com/paper/2307.12493/) (2023)
- [AMT: All-Pairs Multi-Field Transforms for Efficient Frame Interpolation](https://mlsanity.com/paper/2304.09790/) (2023)
- [MoSca: Dynamic Gaussian Fusion from Casual Videos via 4D Motion Scaffolds](https://mlsanity.com/paper/2405.17421/) (2024)
- [Recurrent Video Restoration Transformer with Guided Deformable Attention](https://mlsanity.com/paper/2206.02146/) (2022)
- [Frame-Recurrent Video Super-Resolution](https://mlsanity.com/paper/1801.04590/) (2018)
- [HunyuanVideo 1.5 Technical Report](https://mlsanity.com/paper/2511.18870/) (2025)
- [Real-Time Video Super-Resolution with Spatio-Temporal Networks and Motion Compensation](https://mlsanity.com/paper/1611.05250/) (2016)
- [FILM: Frame Interpolation for Large Motion](https://mlsanity.com/paper/2202.04901/) (2022)

## Built on by (most cited first, 1 of 1)

- [PhoenixSR: Generative Heterogeneous Distillation Unleashes Efficient Models for Real-World Super-Resolution](https://mlsanity.com/paper/2609.30988/) (2026)

## Abstract (arXiv)

Continuous Spatio-Temporal Video Super-Resolution (C-STVSR) aims to simultaneously enhance the spatial resolution and frame rate of videos by arbitrary scale factors, offering greater flexibility than fixed-scale methods that are constrained by predefined upsampling ratios. In recent years, methods based on Implicit Neural Representations (INR) have made significant progress in C-STVSR by learning continuous mappings from spatio-temporal coordinates to pixel values. However, these methods fundamentally rely on dense pixel-wise grid queries, causing computational cost to scale linearly with the number of interpolated frames and severely limiting inference efficiency. We propose GS-STVSR, an ultra-efficient C-STVSR framework based on 2D Gaussian Splatting (2D-GS) that drives the spatiotemporal evolution of Gaussian kernels through continuous motion modeling, bypassing dense grid queries entirely. We exploit the strong temporal stability of covariance parameters for lightweight intermediate fitting, design an optical flow-guided motion module to derive Gaussian position and color at arbitrary time steps, introduce a Covariance resampling alignment module to prevent covariance drift, and propose an adaptive offset window for large-scale motion. Extensive experiments on Vid4, GoPro, and Adobe240 show that GS-STVSR achieves state-of-the-art quality across all benchmarks. Moreover, its inference time remains nearly constant at conventional temporal scales (X2--X8) and delivers over X3 speedup at extreme scales X32, demonstrating strong practical applicability.