← Search

Tim Salzmann

7 accepted papers

2024

Normalizing Flows on the Product Space of SO(3) Manifolds for Probabilistic Human Pose Modeling

CVPR 2024poster

Normalizing flows have proven their efficacy for density estimation in Euclidean space but their application to rotational representations crucial in various domains such as robotics or human pose modeling remains underexplored. Probabilistic models of the human pose can benefit from approaches that…

2024

Scene-Graph ViT: End-to-End Open-Vocabulary Visual Relationship Detection

ECCV 2024poster

"f igure.pdf Figure 1: Relationships [width=]figures/hero detected by our method on an unseen image. The top relationships by confidence score are shown. Photo by Spacejoy on Unsplash. Visual relationship detection aims to identify objects and their relationships in images. Prior methods approach th…

Cited by 4SourcePDFScholar
2023

Real-Time Neural MPC: Deep Learning Model Predictive Control for Quadrotors and Agile Robotic Platforms

RA-L 2023

Model Predictive Control (MPC) has become a popular framework in embedded control for high-performance autonomous systems. However, to achieve good control performance using MPC, an accurate dynamics model is key. To maintain real-time operation, the dynamics models used on embedded systems have bee

Cited by 204SourceScholar
2023

Robots That Can See: Leveraging Human Pose for Trajectory Prediction

RA-L 2023

Anticipating the motion of all humans in dynamic environments such as homes and offices is critical to enable safe and effective robot navigation. Such spaces remain challenging as humans do not follow strict rules of motion and there are often multiple occluded entry points such as corners and door

Cited by 39SourcecodeScholar
2020

Trajectron++: Dynamically-Feasible Trajectory Forecasting With Heterogeneous Data

ECCV 2020poster

Reasoning about human motion is an important prerequisite to safe and socially-aware robotic navigation. As a result, multi-agent behavior prediction has become a core component of modern human-robot interactive systems, such as self-driving cars. While there exist many methods for trajectory foreca…