Alex Costanzino

I received my BSc degree in Automation Engineering from the University of Bologna in 2020, with a thesis on predictive maintenance of bearing rings through the analysis of acceleration signals using Bayesian classifiers.

I then received my MSc degree in Artificial Intelligence from the University of Bologna in 2022, with a thesis on mitigating the issues caused by non-Lambertian surfaces in Stereo Matching using Neural Radiance Fields.

In 2025, I received my PhD in Computer Science and Engineering from the University of Bologna, under the supervision of Luigi Di Stefano, with a thesis titled Neural Understanding of Objects and Materials.

I am currently a postdoctoral researcher in the Computer Vision Group at the University of Bonn, led by Jürgen Gall, and a member of the Lamarr Institute for Machine Learning and Artificial Intelligence. Previously, I was a postdoctoral researcher at the Computer Vision Lab at the University of Bologna.

My research lies at the intersection of Computer Vision and Machine Learning, with a broad interest in developing intelligent systems capable of understanding and reasoning about the visual world.

news

Jun 18, 2026	Our paper Spectral Gating via Damped Oscillations for Adaptive Implicit Neural Representations has been accepted at ECCV 2026 as a Spotlight Oral! Stay tuned on the project page.
Mar 20, 2026	Our paper Modulate-and-Map: Crossmodal Feature Mapping with Cross-View Modulation for 3D Anomaly Detection has been accepted at CVPR Findings 2026! More on the project page.
Oct 19, 2025	Our paper Towards Reliable Identification of Diffusion-based Image Manipulations has been accepted at NeurIPS 2025! Check out the project page.
Jul 20, 2025	Our paper SiM3D: Single-instance Multiview Multimodal and Multisetup 3D Anomaly Detection Benchmark has been accepted at ICCV 2025! See the project page.
Apr 23, 2025	Our workshop Transparent & Reflective objects In the wild Challenges (TRICKY) has been accepted at ICCVW 2025! More info on the website.