Benchmarks
Greatest papers with code
Learning Temporal Coherence via Self-Supervision for GAN-based Video Generation
• thunil/TecoGAN
• 
Additionally, we propose a first set of metrics to quantitatively evaluate the accuracy as well as the perceptual quality of the temporal evolution.
IMAGE SUPER-RESOLUTION MOTION COMPENSATION VIDEO GENERATION VIDEO SUPER-RESOLUTION
Tracking without bells and whistles
ICCV 2019
• phil-bergmann/tracking_wo_bnw
•
We then perform an analysis on the performance and failure cases of several state-of-the-art tracking methods in comparison to our Tracktor.
Ranked #1 on
Online Multi-Object Tracking
on MOT17
Detail-revealing Deep Video Super-resolution
ICCV 2017
• jiangsutx/SPMC_VideoSR
• 
In this paper, we show that proper frame alignment and motion compensation is crucial for achieving high quality results.
Ranked #7 on
Video Super-Resolution
on Vid4 - 4x upscaling
IMAGE SUPER-RESOLUTION MOTION COMPENSATION VIDEO SUPER-RESOLUTION
FastDVDnet: Towards Real-Time Deep Video Denoising Without Flow Estimation
CVPR 2020
• m-tassano/fastdvdnet
•
In this paper, we propose a state-of-the-art video denoising algorithm based on a convolutional neural network architecture.
Ranked #1 on
Video Denoising
on Set8 sigma10
DENOISING MOTION COMPENSATION MOTION ESTIMATION VIDEO DENOISING
Deep Video Super-Resolution Network Using Dynamic Upsampling Filters Without Explicit Motion Compensation
We propose a novel end-to-end deep neural network that generates dynamic upsampling filters and a residual image, which are computed depending on the local spatio-temporal neighborhood of each pixel to avoid explicit motion compensation.
Ranked #2 on
Video Super-Resolution
on Vid4 - 4x upscaling
DATA AUGMENTATION MOTION COMPENSATION MOTION ESTIMATION VIDEO SUPER-RESOLUTION
Deformable 3D Convolution for Video Super-Resolution
• XinyiYing/D3Dnet
•
In this paper, we propose a deformable 3D convolution network (D3Dnet) to incorporate spatio-temporal information from both spatial and temporal dimensions for video SR.
Deep Video Super-Resolution using HR Optical Flow Estimation
The key challenge for video SR lies in the effective exploitation of temporal dependency between consecutive frames.
Ranked #8 on
Video Super-Resolution
on Vid4 - 4x upscaling
MOTION COMPENSATION OPTICAL FLOW ESTIMATION VIDEO SUPER-RESOLUTION
Learning for Video Super-Resolution through HR Optical Flow Estimation
Extensive experiments demonstrate that HR optical flows provide more accurate correspondences than their LR counterparts and improve both accuracy and consistency performance.
Ranked #9 on
Video Super-Resolution
on Vid4 - 4x upscaling
MOTION COMPENSATION OPTICAL FLOW ESTIMATION VIDEO SUPER-RESOLUTION
Progressive Fusion Video Super-Resolution Network via Exploiting Non-Local Spatio-Temporal Correlations
Most previous fusion strategies either fail to fully utilize temporal information or cost too much time, and how to effectively fuse temporal information from consecutive frames plays an important role in video super-resolution (SR).
MOTION COMPENSATION MOTION ESTIMATION VIDEO SUPER-RESOLUTION
MEMC-Net: Motion Estimation and Motion Compensation Driven Neural Network for Video Frame Interpolation and Enhancement
arXiv 2018
• baowenbo/MEMC-Net
•
In this work, we propose a motion estimation and motion compensation driven neural network for video frame interpolation.
Ranked #5 on
Video Frame Interpolation
on Middlebury
DENOISING MOTION COMPENSATION MOTION ESTIMATION OPTICAL FLOW ESTIMATION SUPER-RESOLUTION VIDEO ENHANCEMENT VIDEO FRAME INTERPOLATION