4 papers · 1 filter
TrustCLIP: Learning Private Visual Features via Adversarial Reconstruction
Nikos Athanasiou, Ilya A. Petrov, Angela Yao +7
Vision and vision-language models rely on high-level visual representations that are increasingly used across recognition, retrieval, and multimodal reasoning pipelines. However, r…
Ordered Diffusion for 3D Human Registration
Mattia Masiero, Ilya A. Petrov, Daniel Cremers +2
3D human registration has historically been treated as a regression task, assuming a unique ground-truth alignment exists between the template and an input point cloud. In reality,…
TriDi: Trilateral Diffusion of 3D Humans, Objects, and Interactions
Ilya A. Petrov, Riccardo Marin, Julian Chibane +1
Modeling 3D human-object interaction (HOI) is a problem of great interest for computer vision and a key enabler for virtual and mixed-reality applications. Existing methods work in…
FORCE: Physics-aware Human-object Interaction
Xiaohan Zhang, Bharat Lal Bhatnagar, Sebastian Starke +5
Interactions between human and objects are influenced not only by the object's pose and shape, but also by physical attributes such as object mass and surface friction. They introd…