Trending Research
Robust Speech Recognition via Large-Scale Weak Supervision
openai/whisper
•
•
Preprint 2022
We study the capabilities of speech processing systems trained simply to predict large amounts of transcripts of audio on the internet.
VToonify: Controllable High-Resolution Portrait Video Style Transfer
Although a series of successful portrait image toonification models built upon the powerful StyleGAN have been proposed, these image-oriented methods have obvious limitations when applied to videos, such as the fixed frame size, the requirement of face alignment, missing non-facial details and temporal inconsistency.
Plenoxels: Radiance Fields without Neural Networks
kakaobrain/NeRF-Factory
•
•
CVPR 2022
We introduce Plenoxels (plenoptic voxels), a system for photorealistic view synthesis.
LAVIS: A Library for Language-Vision Intelligence
salesforce/lavis
•
•
We introduce LAVIS, an open-source deep learning library for LAnguage-VISion research and applications.
DINO: DETR with Improved DeNoising Anchor Boxes for End-to-End Object Detection
Compared to other models on the leaderboard, DINO significantly reduces its model size and pre-training data size while achieving better results.
Ranked #1 on
Object Detection
on COCO minival
(using extra training data)
Poisson Flow Generative Models
We interpret the data points as electrical charges on the $z=0$ hyperplane in a space augmented with an additional dimension $z$, generating a high-dimensional electric field (the gradient of the solution to Poisson equation).
Text2Light: Zero-Shot Text-Driven HDR Panorama Generation
To achieve super-resolution inverse tone mapping, we derive a continuous representation of 360-degree imaging from the LDR panorama as a set of structured latent codes anchored to the sphere.
SegNeXt: Rethinking Convolutional Attention Design for Semantic Segmentation
visual-attention-network/segnext
•
•
Notably, SegNeXt outperforms EfficientNet-L2 w/ NAS-FPN and achieves 90. 6% mIoU on the Pascal VOC 2012 test leaderboard using only 1/10 parameters of it.
Ranked #1 on
Semantic Segmentation
on PASCAL VOC 2012 test
DreamBooth: Fine Tuning Text-to-Image Diffusion Models for Subject-Driven Generation
XavierXiao/Dreambooth-Stable-Diffusion
•
•
Once the subject is embedded in the output domain of the model, the unique identifier can then be used to synthesize fully-novel photorealistic images of the subject contextualized in different scenes.
towhee
towhee-io/towhee
•
•
CVPR 2022
Towhee is a framework that is dedicated to making neural data processing pipelines simple and fast.
