Christian Holz
@christianholz.bsky.social
associate professor @ ETH Zürich. sensing, interaction & perception lab https://siplab.org. computational VR/AR input, egocentric perception, predictive mobile health, HCI
We generated 119h of footage using EgoSim across 4 high-fidelity virtual environments with high realism.
Our baseline method—a simple multi-view video pose transformer—directly regresses full-body 3D poses from 6 egocentric videos with solid accuracy, showing EgoSim's effective data generation.
Our baseline method—a simple multi-view video pose transformer—directly regresses full-body 3D poses from 6 egocentric videos with solid accuracy, showing EgoSim's effective data generation.
February 24, 2025 at 8:15 PM
We generated 119h of footage using EgoSim across 4 high-fidelity virtual environments with high realism.
Our baseline method—a simple multi-view video pose transformer—directly regresses full-body 3D poses from 6 egocentric videos with solid accuracy, showing EgoSim's effective data generation.
Our baseline method—a simple multi-view video pose transformer—directly regresses full-body 3D poses from 6 egocentric videos with solid accuracy, showing EgoSim's effective data generation.
Releasing EgoSim, a simulator for body-worn cameras. #NeurIPS2024
EgoSim takes real mocap data (e.g., from 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).
EgoSim takes real mocap data (e.g., from 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).
February 24, 2025 at 8:15 PM
Releasing EgoSim, a simulator for body-worn cameras. #NeurIPS2024
EgoSim takes real mocap data (e.g., from 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).
EgoSim takes real mocap data (e.g., from 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).
EgoPoser proposes spatio-temporal input decomposition to robustly estimate position-invariant poses. We also explicit model headset FOV to account for tracking dropouts.
Our SlowFast feature fusion samples input signals sparsely & densely to extend the input context with no computational overhead.
Our SlowFast feature fusion samples input signals sparsely & densely to extend the input context with no computational overhead.
November 26, 2024 at 4:44 PM
EgoPoser proposes spatio-temporal input decomposition to robustly estimate position-invariant poses. We also explicit model headset FOV to account for tracking dropouts.
Our SlowFast feature fusion samples input signals sparsely & densely to extend the input context with no computational overhead.
Our SlowFast feature fusion samples input signals sparsely & densely to extend the input context with no computational overhead.
EgoPoser is a novel method for accurate full-body pose estimation—purely from egocentric capture of head & hand poses (even when out of view)
#ECCV2024
EgoPoser supports diverse body shapes & remains robust even when users move in large environments
@jiaxijiang.bsky.social @paulstreli.bsky.social
#ECCV2024
EgoPoser supports diverse body shapes & remains robust even when users move in large environments
@jiaxijiang.bsky.social @paulstreli.bsky.social
November 26, 2024 at 4:44 PM
EgoPoser is a novel method for accurate full-body pose estimation—purely from egocentric capture of head & hand poses (even when out of view)
#ECCV2024
EgoPoser supports diverse body shapes & remains robust even when users move in large environments
@jiaxijiang.bsky.social @paulstreli.bsky.social
#ECCV2024
EgoPoser supports diverse body shapes & remains robust even when users move in large environments
@jiaxijiang.bsky.social @paulstreli.bsky.social