AI Technology & Industry Review
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 recently proposed U^2-Net, a novel deep network architecture that achieves very competitive performance in salient 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.
A new AI-powered image synthesis framework makes “learning” to moonwalk or drop Blackpink dance moves a snap.
Stylized Neural Painter is a novel automatic image-to-painting translation method that generates vivid and realistic artworks in controllable styles
“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 AI yesterday released its Objectron dataset — a collection of short, object-centric video clips capturing a large set of common objects from different angles.
Researchers introduced a modular primitive that uses existing, highly optimized hardware graphics pipelines to deliver performance superior to previous differentiable rendering systems.
A team of researchers from Shanghai Jiao Tong University (SJTU) has built a lightweight benchmark suite designed to help make life-saving models of medical image analysis even stronger.
NeurIPS 2020 Institute of Automation CAS and Microsoft Research Asia paper presents an attention-based decoder that integrates CV object representations
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 proposes LambdaNetworks, a transformer-specific method that reduces costs of modeling long-range interactions for CV and other applications.
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.
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 submitted paper proposes efficient VAEs that outperform PixelCNN-based autoregressive models in log-likelihood on natural image benchmarks.
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 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 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.
Novel model uses a quality estimator and evolutionary optimization to search the latent space of GANs trained on limited datasets.
Imaginaire, a universal PyTorch library designed for various GAN-based tasks and methods.
Chinese researchers propose a novel regression framework in pursuit of “fast, accurate and stable 3D dense face alignment simultaneously.”
VR and AR will converge to combine the real and virtual, as Facebook Reality Labs researchers, developers, and engineers aim to change how we see the world.
Synced has identified a few significant technical advancements in the 3D photo field that we believe may be of interest to our readers.
UIUC, Adobe Research and University of Oregon propose HDMatt, a Deep Learning-based image matting Cross-Patch Context module for high-resolution image inputs.
A group of researchers from Google Research and the University of Oxford have introduced a novel technique that can “retiming” people’s movements in videos.
From an augmented view of an image, the researchers trained the online network to predict the target network representation of the same image under a different augmented view.
Researchers have introduced a novel network architecture for jointly estimating the shape and pose of vehicles even from partial LiDAR observations.
Researchers introduced a novel flow-based video completion algorithm that compares favourably with the state-of-the-art in the field.
This research proposes an efficient and cost-effective solution for multi-frame video interpolation.
“Wav2Lip,” a novel lip-synchronization model that outperforms current approaches by a large margin in both quantitative metrics and human evaluations.
Researcher composes a quantitative survey of the SOTA in sign language recognition (SLR).
Intel Labs researchers have proposed a novel method for building a robot called “OpenBot” on just a US$50 budget.
Researchers proposed a new model that is designed to spot deepfakes by looking at subtle visual artifacts.
A novel volumetric capture system that is capable of fully capturing clothed human bodies in real-time using only a single RGB webcam.
The 16th European Conference on Computer Vision (ECCV) kicked off on Sunday as a fully online conference. In the Conference Opening Session this morning, the ECCV organizing committee announced the conference’s paper submission stats and Best Paper selections.
Researchers from The Chinese University of Hong Kong, Facebook Reality Labs, and Facebook AI Research have unveiled a state-of-the-art monocular 3D hand motion capture method, FrankMocap, which can estimate both 3D hand and body motions from in-the-wild monocular inputs with faster speed and better accuracy than previous approaches.
Researchers developed a head-neck combined HR-MRVWI technique that could potentially provide remarkable suppression of cerebrospinal fluid signals.
Elon Musk tweeted that Tesla is recruiting AI or chip talents for the company’s neural network training supercomputer project “Dojo.”
To adapt conventional deep models to real scenarios, a research work carried by a team (XPixel) from the Shenzhen Institutes of Advanced Technology (SIAT) of the Chinese Academy of Sciences investigated the use of additional branches to tune imagery effects.
HoliCity, a city-scale dataset and all-in-one data platform for research into learning abstracted high-level holistic 3D structures derived from city CAD (computer-aided design) models.