collaborators

7 papers

cs.CV2026

TrustCLIP: Learning Private Visual Features via Adversarial Reconstruction

Nikos Athanasiou, Ilya A. Petrov, Angela Yao +8

Vision and vision-language models rely on high-level visual representations that are increasingly used across recognition, retrieval, and multimodal reasoning pipelines. However, r…

cs.CV2026

UniCon3R: Unified Contact-aware 4D Human-Scene Reconstruction from Monocular Video

Tanuj Sur, Shashank Tripathi, Nikos Athanasiou +4

We introduce UniCon3R, a unified feed-forward framework for online human-scene 4D reconstruction from monocular video. Current feed-forward human-scene reconstruction methods suffe…

cs.CV2026

Emotional Speech-driven 3D Body Animation via Disentangled Latent Diffusion

Kiran Chhatre, Radek Daněček, Nikos Athanasiou +4

Existing methods for synthesizing 3D human gestures from speech have shown promising results, but they do not explicitly model the impact of emotions on the generated gestures. Ins…

cs.CV2026

Contact-Aware Refinement of Human Pose Pseudo-Ground Truth via Bioimpedance Sensing

Maria-Paola Forte, Nikos Athanasiou, Giulia Ballardini +3

Capturing accurate 3D human pose in the wild would provide valuable data for training pose estimation and motion generation methods. While video-based estimation approaches have be…

cs.CV2026

FUSION: Full-Body Unified Motion Prior for Body and Hands via Diffusion

Enes Duran, Nikos Athanasiou, Muhammed Kocabas +2

Hands are central to interacting with our surroundings and conveying gestures, making their inclusion essential for full-body motion synthesis. Despite this, existing human motion…

cs.CV2025

FormCoach: Lift Smarter, Not Harder

Xiaoye Zuo, Nikos Athanasiou, Ginger Delmas +3

Good form is the difference between strength and strain, yet for the fast-growing community of at-home fitness enthusiasts, expert feedback is often out of reach. FormCoach transfo…