https://paperswithcode.com/

 
 

  * [                    ] [                    ]
  * Browse State-of-the-Art
  * Datasets
  * Methods
  * More
    Newsletter RC2021
    About Trends Portals Libraries
  * We are hiring!

  *  
  *  
  * Sign In

Subscribe to the PwC Newsletter

x
Stay informed on the latest trending ML papers with code, research
developments, libraries, methods, and datasets.

Read previous issues
[                    ]
Subscribe
Join the community

x
You need to log in to edit.
You can create a new account if you don't have one.

Or, discuss a change on Slack.
 
Top
 
Social
 
New
 
Greatest

Trending Research

Subscribe
 

GLIDE: Towards Photorealistic Image Generation and Editing with
Text-Guided Diffusion Models

openai/glide-text2im * [pytorch-2f] * 20 Dec 2021

Diffusion models have recently been shown to generate high-quality
synthetic images, especially when paired with a guidance technique to
trade off diversity for fidelity.

[task-00000] Image Inpainting

936
2.35 stars / hour
Paper
Code
 

WeNet: Production oriented Streaming and Non-streaming End-to-End
Speech Recognition Toolkit

PaddlePaddle/PaddleSpeech * [paddle-551] * 2 Feb 2021

In this paper, we propose an open source, production first, and
production ready speech recognition toolkit called WeNet in which a
new two-pass approach is implemented to unify streaming and
non-streaming end-to-end (E2E) speech recognition in a single model.

[default] End-To-End Speech Recognition [task-00000] Speech
Recognition

2,263
2.10 stars / hour
Paper
Code
 

First-Pass Large Vocabulary Continuous Speech Recognition using
Bi-Directional Recurrent DNNs

PaddlePaddle/DeepSpeech * [paddle-551] * 12 Aug 2014

This approach to decoding enables first-pass speech recognition with
a language model, completely unaided by the cumbersome infrastructure
of HMM-based systems.

[default] Large Vocabulary Continuous Speech Recognition [task-00000]
Speech Recognition

2,260
1.99 stars / hour
Paper
Code
 

JoJoGAN: One Shot Face Stylization

mchong6/JoJoGAN * [pytorch-2f] * arXiv 2021

While there have been recent advances in few-shot image stylization,
these methods fail to capture stylistic details that are obvious to
humans.

[task-00000] Face Generation [default] GAN inversion +2

343
1.81 stars / hour
Paper
Code
 

High-Resolution Image Synthesis with Latent Diffusion Models

compvis/latent-diffusion * [pytorch-2f] * 20 Dec 2021

By decomposing the image formation process into a sequential
application of denoising autoencoders, diffusion models (DMs) achieve
state-of-the-art synthesis results on image data and beyond.

[task-00000] Denoising [task-00000] Image Inpainting +2

250
1.30 stars / hour
Paper
Code
 

StyleSwin: Transformer-based GAN for High-resolution Image Generation

microsoft/StyleSwin * arXiv 2021

To this end, we believe that local attention is crucial to strike the
balance between computational efficiency and modeling capacity.

[image-gene]  Ranked #1 on Image Generation on CelebA-HQ 1024x1024

[task-00000] Image Generation

199
1.14 stars / hour
Paper
Code
 

Towards Real-World Blind Face Restoration with Generative Facial
Prior

TencentARC/GFPGAN * [pytorch-2f] * CVPR 2021

Blind face restoration usually relies on facial priors, such as
facial geometry prior or reference prior, to restore realistic and
faithful details.

[blind-face]  Ranked #1 on Blind Face Restoration on CelebA-Test

[task-00000] Blind Face Restoration [default] GAN inversion

14,079
1.08 stars / hour
Paper
Code
 

Plenoxels: Radiance Fields without Neural Networks

sxyu/svox2 * [pytorch-2f] * 9 Dec 2021

We introduce Plenoxels (plenoptic voxels), a system for
photorealistic view synthesis.

[default] 2D Object Detection

718
1.02 stars / hour
Paper
Code
 

Omnizart: A General Toolbox for Automatic Music Transcription

Music-and-Culture-Technology-Lab/omnizart * 1 Jun 2021

We present and release Omnizart, a new Python library that provides a
streamlined solution to automatic music transcription (AMT).

[default] Chord Recognition [task-00000] Information Retrieval +2

1,025
0.68 stars / hour
Paper
Code
 

HyperNeRF: A Higher-Dimensional Representation for Topologically
Varying Neural Radiance Fields

google/hypernerf * [jax-6ee30f] * 24 Jun 2021

A common approach to reconstruct such non-rigid scenes is through the
use of a learned deformation field mapping from coordinates in each
input image into a canonical template coordinate space.

[task-00000] Novel View Synthesis

283
0.59 stars / hour
Paper
Code
 
Contact us on: hello@paperswithcode.com . Papers With Code is a free
resource with all data licensed under CC-BY-SA.
Terms Data policy Cookies policy from