8 papers · 1 filter
Resonant Brane Splatting for Arbitrary-Scale Super-Resolution
Giulio Federico, Giuseppe Amato, Claudio Gennaro +2
Arbitrary-Scale Super-Resolution (ASR) reconstructs images at continuous magnification factors. Recent methods accelerate inference by replacing computationally heavy implicit neur…
Learning to Adaptively Allocate Gaussians for Arbitrary-Scale Image Super-Resolution
Giulio Federico, Giuseppe Amato, Claudio Gennaro +2
In computer graphics, visual content is continuously warped, zoomed and resampled. This occurs when engines upscale frames, users zoom into 3D scenes, or foveated VR applies varyin…
LoomNet: Enhancing Multi-View Image Generation via Latent Space Weaving
Giulio Federico, Fabio Carrara, Claudio Gennaro +2
Generating consistent multi-view images from a single image remains challenging. Lack of spatial consistency often degrades 3D mesh quality in surface reconstruction. To address th…
CA3D: Convolutional-Attentional 3D Nets for Efficient Video Activity Recognition on the Edge
Gabriele Lagani, Fabrizio Falchi, Claudio Gennaro +1
In this paper, we introduce a deep learning solution for video activity recognition that leverages an innovative combination of convolutional layers with a linear-complexity attent…
ViSketch-GPT: Collaborative Multi-Scale Feature Extraction for Sketch Recognition and Generation
Giulio Federico, Giuseppe Amato, Fabio Carrara +2
Understanding the nature of human sketches is challenging because of the wide variation in how they are created. Recognizing complex structural patterns improves both the accuracy…
Exploring Strengths and Weaknesses of Super-Resolution Attack in Deepfake Detection
Davide Alessandro Coccomini, Roberto Caldelli, Fabrizio Falchi +2
Image manipulation is rapidly evolving, allowing the creation of credible content that can be used to bend reality. Although the results of deepfake detectors are promising, deepfa…