Benchmarks
| TREND | DATASET | BEST METHOD | PAPER TITLE | PAPER | CODE | COMPARE |
|---|---|---|---|---|---|---|
|
||||||
|
||||||
|
||||||
|
||||||
|
||||||
|
Datasets
Greatest papers with code
Motion Representations for Articulated Animation
• AliaksandrSiarohin/first-order-model
• 
To facilitate animation and prevent the leakage of the shape of the driving object, we disentangle shape and pose of objects in the region space.
Ranked #1 on
Video Reconstruction
on Tai-Chi-HD (256)
First Order Motion Model for Image Animation
NeurIPS 2019
• AliaksandrSiarohin/first-order-model
•
To achieve this, we decouple appearance and motion information using a self-supervised formulation.
Ranked #1 on
Video Reconstruction
on Tai-Chi-HD
Deep Slow Motion Video Reconstruction with Hybrid Imaging System
In this paper, we address this problem using two video streams as input; an auxiliary video with high frame rate and low spatial resolution, providing temporal information, in addition to the standard main video with low frame rate and high spatial resolution.
OPTICAL FLOW ESTIMATION VIDEO FRAME INTERPOLATION VIDEO RECONSTRUCTION VIDEO SUPER-RESOLUTION
DeepBinaryMask: Learning a Binary Mask for Video Compressive Sensing
In this paper, we propose a novel encoder-decoder neural network model referred to as DeepBinaryMask for video compressive sensing.
COMPRESSIVE SENSING VIDEO COMPRESSIVE SENSING VIDEO RECONSTRUCTION
High Frame Rate Video Reconstruction based on an Event Camera
Based on the abundant event data alongside a low frame rate, easily blurred images, we propose a simple yet effective approach to reconstruct high-quality and high frame rate sharp videos.
Reducing the Sim-to-Real Gap for Event Cameras
ECCV 2020
• TimoStoff/event_cnn_minimal
•
We present strategies for improving training data for event based CNNs that result in 20-40% boost in performance of existing state-of-the-art (SOTA) video reconstruction networks retrained with our method, and up to 15% for optic flow networks.
Bringing Alive Blurred Moments
This network extracts embedded motion information from the blurred image to generate a sharp video in conjunction with the trained recurrent video decoder.
Ranked #13 on
Deblurring
on GoPro
(using extra training data)
Exploiting Structure for Fast Kernel Learning
We propose two methods for exact Gaussian process (GP) inference and learning on massive image, video, spatial-temporal, or multi-output datasets with missing values (or "gaps") in the observed responses.
Video Reconstruction by Spatio-Temporal Fusion of Blurred-Coded Image Pair
The input to our algorithm is a fully-exposed and coded image pair.