AIConfPaper
← Search

Alex Costanzino

4 accepted papers

2025

SiM3D: Single-instance Multiview Multimodal and Multisetup 3D Anomaly Detection Benchmark

Alex Costanzino, Pierluigi Zama Ramirez, Luigi Lella, Matteo Ragaglia, Alessandro Oliva, Giuseppe Lisanti +1
ICCV 2025poster

We propose SiM3D, the first benchmark considering the integration of multiview and multimodal information for comprehensive 3D anomaly detection and segmentation (ADS) where the task is to produce a voxel-based Anomaly Volume. Moreover, SiM3D focuses on a scenario of high interest in manufacturing:…

Cited by 0Source ↗PDF ↗Scholar ↗
2025

Towards Reliable Identification of Diffusion-based Image Manipulations

Alex Costanzino, Woody Bayliss, Juil Sock, Marc Gorriz Blanch, Danijela Horak, Ivan Laptev +2
NeurIPS 2025poster

Changing facial expressions, gestures, or background details may dramatically alter the meaning conveyed by an image. Notably, recent advances in diffusion models greatly improve the quality of image manipulation while also opening the door to misuse. Identifying changes made to authentic images,…

Cited by 0Source ↗code ↗Scholar ↗
2024

Multimodal Industrial Anomaly Detection by Crossmodal Feature Mapping

Alex Costanzino, Pierluigi Zama Ramirez, Giuseppe Lisanti, Luigi Di Stefano
CVPR 2024poster

Recent advancements have shown the potential of leveraging both point clouds and images to localize anomalies. Nevertheless their applicability in industrial manufacturing is often constrained by significant drawbacks such as the use of memory banks which leads to a substantial increase in terms of…

Cited by 23Source ↗PDF ↗Scholar ↗
2023

Learning Depth Estimation for Transparent and Mirror Surfaces

Alex Costanzino, Pierluigi Zama Ramirez, Matteo Poggi, Fabio Tosi, Stefano Mattoccia, Luigi Di Stefano
ICCV 2023poster

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 to estimate depth properly for such surfaces with neural networks, without requiring any ground-truth annotation. We unv…

Cited by 43PDF ↗Scholar ↗