Fourier Feature Mapping Enables MLPs to Learn High-Frequency Functions in Low-Dimensional Domains
Researchers have proposed the use of Fourier feature mapping with MLPs in order to learn high-frequency functions in low-dimensional problem domains.
Category: Computer Vision & Graphics
Local Motion Phases Technique Boosts Basketball Animation Richness and Realism
Researchers have proposed a novel framework that learns fast and dynamic character interactions.
CVPR 2020 Underway, Best Papers Announced
The 2020 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) has announced its best paper awards.
AI Startup Covariant.ai Building ‘Universal AI for Robots’
Covariant last month secured a US$40 million Series B funding round led by Index Ventures to push its total funding to US$67 million.
Facebook and Kaggle Face Backlash After Disqualifying Apparent ‘Deepfake Detection Challenge’ Winner
Facebook and Kaggle are facing an online backlash after the apparent winners of the Deepfake Detection Challenge (DFDC) were disqualified.
Facebook and UC Berkeley Boost CV Performance and Lower Compute Cost With Visual Transformers
A team of researchers from Facebook and UC Berkeley has proposed a new paradigm for computer vision.
ACM SIGGRAPH 2020 Doctoral Dissertation Award Goes to MIT CSAIL’s Tzu-Mao Li for PhD Thesis on Differentiable Visual Computing
ACM SIGGRAPH has honoured MIT CSAIL postdoctoral researcher Li Tzu-Mao with its 2020 Doctoral Dissertation Award for his PhD thesis Differentiable Visual Computing.
DeepFaceDrawing Generates Photorealistic Portraits from Freehand Sketches
A team of researchers from the Chinese Academy of Sciences and the City University of Hong Kong has introduced a local-to-global approach that can generate lifelike human portraits from relatively rudimentary sketches.
Unsupervised Image Classification Approach Outperforms SOTA Methods by ‘Huge Margins’
Researchers from Katholieke Universiteit Leuven in Belgium and ETH Zürich in a recent paper propose a two-step approach for unsupervised classification.
Facebook AI’s DETR Applies Transformers to CV Tasks
Facebook this week released Detection Transformers (DETR), a new approach for object detection and panoptic segmentation tasks that uses a completely different architecture than previous object detection systems.
NVIDIA’s GameGAN Uses AI to Recreate Pac-Man and Other Game Environments
GameGAN, a generative model that learns to visually imitate video game environments by ingesting screenplay and keyboard actions during training.
Breakthrough Colourization Technique Enables Instance-Aware Treatment of Multiple Objects
The research team proposes that colourization performance can be improved dramatically at the instance level for a few reasons.
Researchers Discover Near-Ideal Photon Sources in Silicon Quantum Photonics
The team introduces photon sources fabricated in silicon that meet a variety of requirements for scalable quantum photonics: high purity, high heralding efficiency, and high indistinguishability.
Cross-domain Correspondence Learning for Exemplar-based Image Translation
We present a general framework for exemplar-based image translation, which synthesizes a photo-realistic image from the input in a distinct domain, given an exemplar image.
Bringing Old Photos Back to Life
The proposed method outperforms supervised methods and unsupervised translation methods on restoring real photos.
Self-Supervised ‘Plan2Explore’ RL Agent Achieves SOTA Zero-Shot and Adaptation Performance
Enter Plan2Explore — a self-supervised RL agent designed to quickly generalize to unseen tasks in a zero or few-shot manner.
Nifty Online Tool Animates Your Actions in Real Time
The delightful program can animate a 2D avatar in real-time from a webcam video stream input and has garnered 3,700 GitHub stars since its release.
House-GAN: Relational Generative Adversarial Networks for Graph-constrained House Layout Generation
This paper proposes a novel graph-constrained generative adversarial network, whose generator and discriminator are built upon relational architecture.
Epic-Kitchens | Largest Egocentric Video Dataset Gets New Baselines
Researchers from the University of Bristol, the University of Toronto and the University of Catania explain how they created Epic-Kitchens and introduce new baselines that emphasize the multimodal nature of the largest such egocentric video benchmark.
New TTNet Table Tennis Model Accelerates DL in Sports Analysis
A team of researchers from Russian AI startup OSAI recently introduced the real-time neural network TTNet, designed for processing high-resolution table tennis videos with both temporal and spatial data.
Consistent Video Depth Estimation: Generating HQ Depth Maps From Single Video Input
Researchers from the University of Washington, Virginia Tech and Facebook have introduced an algorithm that can reconstruct dense, geometrically consistent depth for all pixels in monocular videos.
VidPress: Baidu’s New AI Tool Creating Videos from a URL with One-Click
VidPress is an AI-powered video synthesis tool Baidu Research recently developed in an effort to churn out sleek, professional video content in one click.
Clova AI Releases StarGAN v2 Code, Pretrained Models and Datasets
South Korea’s Naver Clova AI Research is one of the institutions behind the unsupervised generative network U-GAT-IT. The tech hasContinue Reading
YOLO Is Back! Version 4 Boasts Improved Speed and Accuracy
YOLOv4 is twice as fast as EfficientDet with comparable performance.
Turing Award | A Closer Look Into Edwin Catmull’s PhD Thesis
In this article, we take a look at Edwin Catmull’s doctoral dissertation published in 1974, which laid the groundwork for 3D computer graphics.
Creating ‘Yuru-Chara’ and a New Class Conditional GAN Approach For Small Datasets
Researchers have proposed a new and inexpensive method for automatically generating yuru-chara characters.
Landing AI ‘Social Distancing Detector’ Monitors Workplaces
Silicon Valley based Landing AI introduced a new AI-enabled social distancing detection tool designed to help monitor and enforce physical distancing protocols in workplaces.
Stephen Wolfram: The Path to a Fundamental Theory of Physics May Begin With a Hypergraph
Wolfram announced this week that he may have found a path that leads to a fundamental theory of physics, and that it is “beautiful.”
Unsupervised Image-to-Image Translation Turns Selfies Into Anime Characters
Anyone can simply upload a selfie to the ‘Selfie 2 Waifu’ website to create their own AI-generated waifu-style anime character in seconds.
OpenAI Puts CV Models Under Their Microscope
Just as biologists gain insights into organisms by putting model specimens under their microscopes, AI Microscope was designed to help researchers analyze the features that form inside leading CV models.
Hi-Res Image-To-Image Daytime Translation Without Labels
In a bid to generate high-resolution images showing realistic daytime changes while keeping accurate scene semantics, researchers have proposed a novel image-to-image translation model, HiDT (High Resolution Daytime Translation).
‘Active Neural Slam’ Uses Classical and Learning Approaches to Explore 3D Spaces
Researchers have introduced Active Neural SLAM, a modular and hierarchical approach to learning policies for exploring 3D environments.
New NVIDIA and Heidelberg University Viewpoint Estimation Technique Learns From Unlabelled Images
A team of researchers from NVIDIA and Heidelberg University recently introduced an open-source self-supervised learning technique for viewpoint estimation of general objects that draws on such freely available Internet images.
AI Transforms RGB-D Images Into an Impressive 3D Format
Researchers from Virginia Tech, National Tsing Hua University and Facebook have introduced a game-changing algorithm that generates impressive 3D photos from a single RGB-D (colour and depth) image.
AI-Powered Digital People
Synced has identified some interesting AI-powered virtual humans to introduce to our readers.
Use the Force! AI Predicts Human-Object Contact Points and Forces From Video
In a new study, researchers use a physics simulator to learn to predict physical forces in videos of humans interacting with objects.
Deep Fashion3D: Dataset & Benchmark for Virtual Clothing Try-On and More
Deep Fashion3D contains 2,078 3D garment models reconstructed from real-world garments in 10 different clothing categories.
Improving Image Matching: New Open-Source Benchmark with 30K Images
The new benchmark for wide-baseline image matching includes a 30k image dataset with depth maps and accurate pose information.
DarwinAI Open-Sources COVID-Net as Medical Imaging in COVID-19 Diagnosis Debate Continues
Researchers recently developed and open-sourced COVID-Net, a convolutional neural network for detecting COVID-19 through chest radiography.
‘Front2Back’ AI Reconstructs 3D Shapes from 2D Images
Their proposed framework outperforms state-of-the-art approaches for 3D reconstructions from 2D and 2.5D data, achieving 12 percent better performance on average in the ShapeNet benchmark dataset and up to 19 percent for certain classes of objects.