Giorgos Karvounas

Giorgos Karvounas, Nikolaos Kyriazis, Iason Oikonomidis et al.

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.

Giorgos Karvounas, Nikolaos Kyriazis, Iason Oikonomidis et al.

The amount and quality of datasets and tools available in the research field of hand pose and shape estimation act as evidence to the significant progress that has been made.However, even the datasets of the highest quality, reported to date, have shortcomings in annotation. We propose a refinement approach, based on differentiable ray tracing,and demonstrate how a high-quality publicly available, multi-camera dataset of hands(InterHand2.6M) can become an even better dataset, with respect to annotation quality. Differentiable ray tracing has not been employed so far to relevant problems and is hereby shown to be superior to the approximative alternatives that have been employed in the past. To tackle the lack of reliable ground truth, as far as quantitative evaluation is concerned, we resort to realistic synthetic data, to show that the improvement we induce is indeed significant. The same becomes evident in real data through visual evaluation.

Sergiu Oprea, Giorgos Karvounas, Pablo Martinez-Gonzalez et al.

We present HandGAN (H-GAN), a cycle-consistent adversarial learning approach implementing multi-scale perceptual discriminators. It is designed to translate synthetic images of hands to the real domain. Synthetic hands provide complete ground-truth annotations, yet they are not representative of the target distribution of real-world data. We strive to provide the perfect blend of a realistic hand appearance with synthetic annotations. Relying on image-to-image translation, we improve the appearance of synthetic hands to approximate the statistical distribution underlying a collection of real images of hands. H-GAN tackles not only the cross-domain tone mapping but also structural differences in localized areas such as shading discontinuities. Results are evaluated on a qualitative and quantitative basis improving previous works. Furthermore, we relied on the hand classification task to claim our generated hands are statistically similar to the real domain of hands.

Giorgos Karvounas, Iason Oikonomidis, Antonis Argyros

We address the problem of temporal localization of repetitive activities in a video, i.e., the problem of identifying all segments of a video that contain some sort of repetitive or periodic motion. To do so, the proposed method represents a video by the matrix of pairwise frame distances. These distances are computed on frame representations obtained with a convolutional neural network. On top of this representation, we design, implement and evaluate ReActNet, a lightweight convolutional neural network that classifies a given frame as belonging (or not) to a repetitive video segment. An important property of the employed representation is that it can handle repetitive segments of arbitrary number and duration. Furthermore, the proposed training process requires a relatively small number of annotated videos. Our method raises several of the limiting assumptions of existing approaches regarding the contents of the video and the types of the observed repetitive activities. Experimental results on recent, publicly available datasets validate our design choices, verify the generalization potential of ReActNet and demonstrate its superior performance in comparison to the current state of the art.