Here is a list of my publications. Click on the title to view the full paper details.
2024 • 2025 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)
Théo Morales, Omid Taheri, Gerard Lacey
We present a Coarse Hand-Object Interaction Representation (CHOIR), a novel, versatile and fully differentiable field for HOI modelling. CHOIR leverages discrete unsigned distances for continuous shape and pose encoding, alongside multivariate Gaussian distributions to represent dense contact maps with few parameters.
hand-object interaction 3D representation diffusion model grasping
2023 • 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)
Siddharth Ravi, Pau Climent-Perez, Théo Morales, Carlo Huesca-Spairani, Kooshan Hashemifard, Francisco Flórez-Revuelta
We present ODIN, a large-scale multi-modal dataset for human behavior understanding using top-view omnidirectional cameras. It features real-life indoor scenarios with synchronized data like RGB, infrared, and depth images, egocentric videos, physiological signals, and 3D scans. Notably, ODIN offers camera-frame 3D human pose estimates for omnidirectional images, a first in the field.
Pose estimation Pipelines Cameras Physiology Recording Pattern recognition
2022 • Workshop on Distribution Shifts, 36th Conference on Neural Information Processing Systems (NeurIPS 2022)
Théo Morales, Gerard Lacey
Computer vision in hand-object pose has diverse applications. Current methods on balanced datasets may not perform well in real-world scenarios. We introduce a benchmark for handling pose distribution shifts and propose meta-learning for adaptation. Results improve over the baseline, but face optimization challenges. Our analysis guides future benchmark work.
hand-object pose meta-learning test-time adaptation computer vision group distribution shifts dexycb grasping benchmark
2020 • IEEE
Théo Morales, Andriy Sarabakha, Erdal Kayacan
Autonomous drone racing faces challenges with traditional gate detection due to varying conditions. This work proposes a semi-synthetic dataset combining real backgrounds and 3D renders for training convolutional neural networks for gate detection.
drone racing unmanned aerial vehicles deep learning convolutional neural networks semi-synthetic images generation
Page designed by Ankit Sultana, modified by K. Lin, and customized by Théo Morales