Making motion capture a lot more practical: Garment Inertial Poser estimates full-body motion from IMUs that are loosely attached to everyday clothing—no cameras, no tight straps. #IJCAI2025 Talk is today in the session "Diffusion models". Andela Ilic @cs_jiaxi_jiang @paulstreli

Releasing EgoSim, a simulator for body-worn cameras. #NeurIPS2024 D&B EgoSim takes real mocap data (e.g., AMASS) and synthesizes multi-modal egocentric videos Plus: MultiEgoView, a real dataset from 6 GoPro cameras and ground-truth 3D poses during several activities (13 people)

Introducing EgoPoser, a novel method for accurate full-body pose estimation—purely from sparse egocentric capture of head & hand poses (even when out of view) #eccv2024 @CSatETH EgoPoser supports diverse body shapes and remains robust even when users move in large environments.

new: MANIKIN reveals & overcomes SMPL-based limitations for full-body IK tasks via – a biomechanically-inspired neural-analytical formulation – a neural IK method for predicting body poses from end-effectors @eccvconf #ECCV2024 @cs_jiaxi_jiang @paulstreli @Xuejingluo @CSatETH

Had an amazing time at #ECCV2024! Presented two papers, got to know brilliant new people, met with super nice previous advisors, and got chances to meet top experts. What an inspiring experience!

new research: Ultra Inertial Poser: Scalable full-body tracking in the wild using sparse sensing #SIGGRAPH2024 No cameras—just 6 wearables (IMU+UWB) for our graph model to estimate poses We are first to process raw IMU signals and need no proprietary sensors for 3D orientation

We introduce Structured Light Speckle, an egocentric and purely optical method that simultaneously discovers surrounding surfaces and contact with them. Our system integrates structured light for depth estimation with laser speckle to resolve remote vibrometry. @CSatETH @ETH_en

Avatar with legs in #VR! We are now showing the demo of our ECCV paper ‘AvatarPoser: Articulated Full-Body Pose Tracking from Sparse Motion Sensing’ in Hall C demo area @eccvconf Paper: https://t.co/yz8iAzC7av Code: https://t.co/Xa2K19p3C0 #metaverse #avatar #vr

Looking forward to my first in-person conference!

I am honored to be awarded the Springorium Commemorative Coin during the graduation ceremony of @RWTH. Thank you, RWTH Aachen❤️

So happy to do this cool project and see it accepted by @eccvconf. Very nice collaboration with @paulstreli, Huajian, @andreas_fender @cholz from @CSatETH @ETH_en and @LarissaLaich @BeRecursive from @RealityLabs! Thank you all!

Is it possible to change the title for the camera-ready version, if not requested by reviewers?@eccvconf I asked PCs but haven’t got a response yet

Do you want to do a Ph.D. in Computer Vision and Deep Learning? Are you interested in doing high-quality research in the heart of Europe? Are you READY for RADU™? Join Prof. Timofte's lab at JMU now! https://t.co/OgU968vZff #Rd4Radu #PhDposition #ComputerVision #DeepLearning

#ECCV2022 list of paper IDs of accepted papers is NOW available! https://t.co/bTJdeqGBYU

So happy to see this work published and presented at #CHI2022! Very nice experience to work with @paulstreli @andreas_fender, Manuel Meier, @HugoRomat and Prof. @cholz !

new research: TapType—put on our wristbands and type anywhere on surrounding surfaces. No cameras involved, which makes TapType an ultra mobile #text #entry method. #CHI2022 @acm_chi w/ @paulstreli @andreas_fender @cs_jiaxi_jiang @HugoRomat @CSatETH @ETH_en

new research: Asynchronous Reality — where everything remains real except the flow of time. #CHI2022 best paper Users interact in the same space but in their individual timelines, opportunistically synchronized as needed. #MixedReality w/@andreas_fender @sigchi @CSatETH @ETH_en

This work was done at the Computer Vision Lab, ETH Zurich @CVL_ETH. Great appreciation to my advisors Dr. Kai Zhang and Prof. Radu Timofte!

Very happy to announce that the work of my master’s thesis “Towards Flexible Blind JPEG Artifacts Removal” is accepted by @ICCV_2021 , and we release the paper and code today at https://t.co/Mw2tNhSHb0 Welcome to check out!