ETH Zurich

A big problem in space research is whether the same stars or galaxies are seen in different sky surveys. Telescopes today gather a ton of data about thousands or even billions of objects using various types...
Providing a virtual environment that matches the actual world, the recent widespread rise of 3D applications, including metaverse, VR/AR, video games, and physical simulators, has improved human lifestyle and increased productive efficiency. These programs are based...

This Artificial Intelligence (AI) Paper Presents a New Metric TETA and a New Model TETer for Tracking Every Thing in the Wild

Estimating the trajectory of items in a video clip is the goal of multiple object tracking (MOT). While specific MOT standards only consider tracking...

Researchers from ETH Zurich and Microsoft Propose ‘LaMAR,’ a New Benchmark for Localization and Mapping for Augmented Reality

Augmented reality (AR) is on its way to becoming a part of our daily lives. We can define it as placing a virtual object...

Latest Natural Language Generation Research Introduces ‘Typical Sampling,’ A New Decoding Method that is Principled, Effective, and can be Implemented Efficiently

Natural language models can model a text corpus C by learning the probability distribution p over all natural language strings Y∈C, with Y={y_1,y_2,y_3...,y_t}. For...

ETH Zurich AI Researchers Introduce ‘tntorch’: a PyTorch-Powered Tensor Learning Python Library That Supports Multiple Decompositions Under a Unified Interface

Tensors are an effective method for handling and representing multidimensional data arrays. However, they have a limitation in terms of storage and computation. Tensor...

ETH Zürich Team Introduces A Novel Method To Decode Text From Accelerometer Signals Sensed At The User’s Wrist Using A Wearable Device

This Article Is Based On The Research 'TapType: Ten-finger text entry on everyday surfaces via Bayesian inference'. All Credit For This Research Goes To...

Researchers Introduce gDNA: a Novel AI Method that Learns to Generate Detailed 3D Shapes of People in a Variety of Garments with Corresponding Skinning...

This article summary is based on the research paper: 'gDNA: Towards Generative Detailed Neural Avatars' All credits for this research goes to the authors of...

ETH Zurich Team Introduce Exemplar Transformers: A New Efficient Transformer Layer For Real-Time Visual Object Tracking

Visual tracking involves estimating the trajectory of an object in a video series, which is one of the fundamental challenges in computer vision. With...

Recent articles