Video Super-Resolution
16개 벤치마크 · 논문 332편 · 이 태스크의 논문 보기 →
Benchmarks
Vid4 - 4x upscaling
REDS4- 4x upscaling
UDM10 - 4x upscaling
Falling Objects
TbD
TbD-3D
Vimeo90K
Xiph HD - 4x upscaling
SAT-MTB-VSR
SPMCS - 4x upscaling
Vimeo-90K
Most implemented
Image Super-Resolution Using Deep Convolutional Networks
Real-Time Single Image and Video Super-Resolution Using an Efficient Sub-Pixel Convolutional Neural Network
ESRGAN: Enhanced Super-Resolution Generative Adversarial Networks
XGBoost: A Scalable Tree Boosting System
Deep Back-Projection Networks For Super-Resolution
Learning Temporal Coherence via Self-Supervision for GAN-based Video Generation
Papers
A Multi-Layer System for Ultra-High-Resolution Static 360-Degree Telepresence
360-degree video telepresence offers strong immersive potential but remains constrained by the limited resolution of current capture and display hardware. Many telepresence installations feature fixed viewpoints and larg…
Video Super-ResolutionNanoVSR: Towards Real-Time Video Super-Resolution on Edge Devices
Recent Video Super-Resolution (VSR) methods rely heavily on transformers and explicit optical flow, creating computational overhead and custom operations that hinder deployment on hardware accelerators like TensorRT. To …
Computational EfficiencyVideo Super-ResolutionAVSR-Diff: Scale-Agnostic Diffusion Priors for Temporally Consistent Arbitrary-Scale Video Super-Resolution
Diffusion models have significantly advanced video super-resolution (VSR) but remain largely constrained to fixed upsampling scales. Conversely, while coordinate-based arbitrary-scale VSR methods offer scale flexibility,…
Video Super-ResolutionDTI: Dynamic Trajectory Initialization for Generative Face Video Super-Resolution
As the most perceptually powerful Face Video Super-Resolution (FVSR) method, existing works in Generative FVSR (GFVSR) mainly exploit the generative prior of pretrained diffusion models. However, viewed as full generatio…
Video Super-ResolutionEvTexture++: Event-Driven Texture Enhancement for Video Super-Resolution
Event-based vision has drawn increasing attention owing to its distinctive properties, including ultra-high temporal resolution and extreme dynamic range. Recent works have introduced it to video super-resolution (VSR) t…
Video Super-ResolutionEvent-based visionLiteVSR: Lightweight Adaptation of Frozen Diffusion Transformers for Video Super-Resolution
Adapting large-scale pre-trained video generators for Video Super-Resolution (VSR) in novel domains remains computationally prohibitive. Methods that reformulate generation as direct Low-Quality to High-Quality mappings …
Video Super-Resolution