Giorgos Karvounas
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Giorgos Karvounas has a total of 5 co-authors. Here are the top co-authors by number of shared publications:
- Antonis Argyros
University of Crete
2 shared publications - Iason Oikonomidis
Foundation for Research and Technology – Hellas (FORTH)
2 shared publications - Georgios Pavlakos
University of Texas at Austin
1 shared publication - Nikolaos Kyriazis
ICS-FORTH
1 shared publication - Vassilis C. Nicodemou
Institute of Computer Science (ICS) Foundation for Research & Technology - Hellas (FORTH) Heraklion Greece
1 shared publication
Latest Publications
- Open Access
Enhancing Monocular 3D Hand Reconstruction with Learned Texture Priors
We revisit the role of texture in monocular 3D hand reconstruction, not as an afterthought for photorealism, but as a dense, spatially grounded cue that can actively support pose and shape estimation. Our observation is simple: even in high-performing models, the overlay between predicted hand geometry and image appearance is often imperfect, suggesting that texture alignment may be an underused supervisory signal. We propose a lightweight texture module that embeds per-pixel observations into UV texture space and enables a novel dense alignment loss between predicted and observed hand appearances. Our approach assumes access to a differentiable rendering pipeline and a model that maps images to 3D hand meshes with known topology, allowing us to back-project a textured hand onto the image and perform pixel-based alignment. The module is self-contained and easily pluggable into existing reconstruction pipelines. To isolate and highlight the value of texture-guided supervision, we augment HaMeR, a high-performing yet unadorned transformer architecture for 3D hand pose estimation. The resulting system improves both accuracy and realism, demonstrating the value of appearance-guided alignment in hand reconstruction.
Open AccessEnhancing Monocular 3D Hand Reconstruction with Learned Texture Priors
We revisit the role of texture in monocular 3D hand reconstruction, not as an afterthought for photorealism, but as a dense, spatially grounded cue that can actively support pose and shape estimation. Our observation is simple: even in high-performing models, the overlay between predicted hand geometry and image appearance is often imperfect, suggesting that texture alignment may be an underused supervisory signal. We propose a lightweight texture module that embeds per-pixel observations into UV texture space and enables a novel dense alignment loss between predicted and observed hand appearances. Our approach assumes access to a differentiable rendering pipeline and a model that maps images to 3D hand meshes with known topology, allowing us to back-project a textured hand onto the image and perform pixel-based alignment. The module is self-contained and easily pluggable into existing reconstruction pipelines. To isolate and highlight the value of texture-guided supervision, we augment HaMeR, a high-performing yet unadorned transformer architecture for 3D hand pose estimation. The resulting system improves both accuracy and realism, demonstrating the value of appearance-guided alignment in hand reconstruction.
- 12 May 2025
- Published by Springer Nature
- p. 85-100
Conditional Hand Image Generation Using Latent Space Supervision in Random Variable Variational Autoencoders
- 12 May 2025
- Published by Springer Nature
- p. 85-100
Conditional Hand Image Generation Using Latent Space Supervision in Random Variable Variational Autoencoders