The Eyes Have It: 20 Million Images Make TEyeD World’s Largest Human Eye Dataset
A new study by University Tübingen introduces the world’s largest unified eye dataset with over 20 million human eye images captured using head-mounted eye trackers.
Category: Computer Vision & Graphics
CHI 2021 | ‘AI as Play’ Challenges the Productivity-Based Human-AI Interaction Paradigm
Researchers from Drexel University, Northeastern University and IT University Copenhagen explore how humans interact with AI in such contexts, with a focus on computer games.
Max Planck Institute & Facebook Model Performs Human Re-Rendering From a Single Image
In a new paper, researchers from Max Planck Institute for Informatics and Facebook Reality Labs propose an end-to-end trainable method that enables re-rendering of humans from one single image.
VisualVoice Uses Facial Appearance to Boost SOTA in Speech Separation
Recent AI research on speech separation has explored ways to associate lip motions in videos with audio, but this approach suffers when speakers’ lips are occluded, which they often are in busy multi-speaker environments.
StyleGAN-Based VOGUE Is a SOTA AI-Powered Fitting Room
VOGUE, an AI-powered optimization method that deforms garments according to a given body shape while preserving pattern and material details to deliver state-of-the-art photorealistic, high-resolution try-on images.
Columbia University Model Learns Predictability From Unlabelled Video
Researchers propose a novel framework and hierarchical predictive model that learns to identify what is predictable from unlabelled video.
‘Neural Body’ Reconstructs Dynamic Human Bodies From Sparse Camera Views
The novel approach tackles dynamic 3D human-body synthesis from a sparse set of camera views, bettering existing methods on key metrics by significant margins.
PGDrive Simulator Generates Unlimited Diverse Driving Environments
Researchers proposed PGDrive, a driving simulator designed to evaluate and improve end-to-end driving agents’ generalization abilities.
2020 in Review With Sheldon Fernandez
Synced has invited Mr. Sheldon Fernandez to share his insights about the current development and future trends of artificial intelligence.
2020 in Review: 10 AI-Powered Art Projects
As part of our year-end series, Synced highlights 10 AI-powered art projects that inspired and entertained us in 2020.
Heidelberg University Researchers Combine CNNs and Transformers to Synthesize High-Resolution Images
Researchers combine the effectiveness of the inductive bias in CNNs with the expressivity of transformers to model and synthesize high resolution images.
‘We Can Do It’ – Geoffrey Hinton and UBC, UT, Google & UVic Team Propose Unsupervised Capsule Architecture for 3D Point Clouds
In the new paper Canonical Capsules: Unsupervised Capsules in Canonical Pose, Turing Award Honoree Dr. Geoffrey Hinton and a team of researchers propose an architecture for unsupervised learning with 3D point clouds based on capsules.
Facebook AI & University of Notre Dame Propose Multi-Face Pose Estimation Without Face Detection
University of Notre Dame and Facebook AI research propose Img2pose, real-time 6DoF 3D face pose estimation without face detection or landmark localization.
Depix AI Recovers Pixelized Passwords, Earns 10K GitHub Stars
“Depix” is a new AI-powered tool that can easily undo pixelization to enable recovery of the information therein.
MIT CSAIL Uses Deep Generative Model StyleGAN2 to Deliver SOTA Image Reconstruction Results
CSAIL researchers propose a framework for image reconstruction tasks using the state-of-the-art generative model StyleGAN2.
This Pizza Does Not Exist: StyleGAN2-Based Model Generates Photo-Realistic Pizza Images
The new AI-powered Multi-Ingredient Pizza Generator (MPG) can deliver all these mouth-watering pies and many more.
NeurIPS 2020: NVIDIA Achieves AI Training Breakthrough Using Limited Datasets of 1,500 Images
NVIDIA blog introduced company’s latest NeurIPS presentation: applying a novel neural network training technique, adaptive discriminator augmentation, to the popular NVIDIA StyleGAN2 model.
NVIDIA Neural Talking-Head Synthesis Makes Video Conferencing 10x More Bandwidth Efficient
The approach dramatically reduces bandwidth requirements by sending only a keypoint representation [of faces] and reconstructing the source video on the receiver side with the help of generative adversarial networks (GANs) to synthesize the talking heads.
Princeton Student’s AI Model Generates Chinese Landscape Paintings That Fool Human Evaluators
A Princeton student designed a GAN framework for Chinese landscape painting generation that is so effective most humans can’t distinguish its works from the real thing.
Facebook Proposes Free-Viewpoint Rendering on Monocular Video
Facebook’s new model enables free-viewpoint rendering of dynamic scenes in a single video.
Do We Really Need Green Screens for High-Quality Real-Time Human Matting?
Researchers from the City University of Hong Kong and SenseTime propose a lightweight matting objective decomposition network (MODNet) that can smoothly process real-time human matting from a single input image with diverse and dynamic backgrounds.
University of Alberta U^2-Net: Generating Realistic Pencil Portraits Using Salient Object Detection
University of Alberta recently proposed U^2-Net, a novel deep network architecture that achieves very competitive performance in salient object detection.
UP-DETR: Unsupervised ‘Random Query Patch Detection’ Pretrains Transformers for Object Detection
A new study by South China University of Technology and Tencent WeChat AI researchers is the latest fruitful attempt to utilize transformer architectures in object detection.
Impersonator++ Human Image Synthesis – Smarten Up Your Dance Moves!
A new AI-powered image synthesis framework makes “learning” to moonwalk or drop Blackpink dance moves a snap.
Automatic Image-to-Painting Translation Method Generates Vivid Paintings in Controllable Styles
Stylized Neural Painter is a novel automatic image-to-painting translation method that generates vivid and realistic artworks in controllable styles
IBM Fine-Grained Visual Recognition Powers AR Tech Support
“Our research provides enriched AR user experiences by enabling a more fine-grained visual recognition feature in AR, which is desirable in a wide range of application scenarios including technical support,” IBM researchers say.
Google Releases ‘Objectron Dataset’ of Object-Centric Video Clips to Advance 3D Object Understanding
Google AI yesterday released its Objectron dataset — a collection of short, object-centric video clips capturing a large set of common objects from different angles.
Nvidia Introduces Modular Primitives for High-Performance Differentiable Rendering
Researchers introduced a modular primitive that uses existing, highly optimized hardware graphics pipelines to deliver performance superior to previous differentiable rendering systems.
AI Halloween Avatars! StyleGAN2 Generator Reveals Your Inner Zombie
Now, just in time for costume season, another indie developer has taken facial image transfer tech to the opposite end of the cuteness spectrum, building a zombie generator.
ICLR 2021 Submission | ‘Lambda Networks’ Achieve SOTA Accuracy, Save Massive Memory
ICLR 2021 submission proposes LambdaNetworks, a transformer-specific method that reduces costs of modeling long-range interactions for CV and other applications.
Google Open-Sources 3D System That Shows How Places Looked in the Past
Google AI recently launched the open-source browser-based toolset “rǝ,” which was created to enable the exploration of city transitions from 1800 to 2000 virtually in a three-dimensional view.
NeurIPS 2020 Workshop | Indie GAN Interpolation Method Turns Selfies Into Cartoon Characters
Pinkney and Adler NeurIPS 2020 workshop paper enables realistic image generation in domains such as animation and ukiyo-e with creative control on the output.
ICLR 2021 Submission: Deeper VAEs Excel on Natural Image Benchmarks
ICLR 2021 submitted paper proposes efficient VAEs that outperform PixelCNN-based autoregressive models in log-likelihood on natural image benchmarks.
‘Farewell Convolutions’ – ML Community Applauds Anonymous ICLR 2021 Paper That Uses Transformers for Image Recognition at Scale
ICLR 2021 paper An Image Is Worth 16×16 Words: Transformers for Image Recognition at Scale suggests Transformers can outperform top CNNs on CV at scale.
Google, Stanford, & MIT Top NeurIPS 2020 Accepted Papers List
NeurIPS 2020 released its list of accepted papers this week with Google, Stanford, and MIT as the top affiliations.
Google AI Helps Sign Language ‘Take the Floor’ in Video Conferences
Google AI researchers developed a sign language detection model for video conferencing applications that can perform real-time identification of a person signing as an active speaker.
Google AI ‘Looking to Listen’ Tech Enables Speech Enhancement on YouTube Stories in Seconds
Google AI has announced a new audiovisual speech enhancement feature in YouTube Stories (iOS) that enables creators to make better selfie videos by automatically enhancing their voices and reducing noise.
EvolGAN Boosts Image Quality for Small or Difficult Datasets
Novel model uses a quality estimator and evolutionary optimization to search the latent space of GANs trained on limited datasets.
Nvidia Releases ‘Imaginaire’ Library for Image and Video Synthesis
Imaginaire, a universal PyTorch library designed for various GAN-based tasks and methods.
Lightweight 3D Dense Face Alignment? New Chinese Model is ‘Fast, Accurate and Stable’
Chinese researchers propose a novel regression framework in pursuit of “fast, accurate and stable 3D dense face alignment simultaneously.”