4 papers
GigaBench: Benchmarking Learnable Representations for Gigapixel Image Compression and Super-Resolution
Matteo Fusconi, Alex Costanzino, Pierluigi Zama Ramirez +1
Learnable Representations (LRs) can fit parametric families of functions to diverse kinds of signals. These emergent neural-native data formats are gathering interest in the scient…
Modulate-and-Map: Crossmodal Feature Mapping with Cross-View Modulation for 3D Anomaly Detection
Alex Costanzino, Pierluigi Zama Ramirez, Giuseppe Lisanti +1
We present ModMap, a natively multiview and multimodal framework for 3D anomaly detection and segmentation. Unlike existing methods that process views independently, our method dra…
Scaling LLaNA: Advancing NeRF-Language Understanding Through Large-Scale Training
Andrea Amaduzzi, Pierluigi Zama Ramirez, Giuseppe Lisanti +2
Recent advances in Multimodal Large Language Models (MLLMs) have shown remarkable capabilities in understanding both images and 3D data, yet these modalities face inherent limitati…
Learning Depth Estimation for Transparent and Mirror Surfaces
Alex Costanzino, Pierluigi Zama Ramirez, Matteo Poggi +3
Inferring the depth of transparent or mirror (ToM) surfaces represents a hard challenge for either sensors, algorithms, or deep networks. We propose a simple pipeline for learning…