This Thesis addresses fundamental challenges in neural understanding of objects and materials through three research domains: depth estimation for non-Lambertian surfaces, anomaly detection and segmentation in advanced industrial settings, and modern image forgery detection and localisation in the era of sophisticated generative models. The work demonstrates that effective visual understanding in complex real-world scenarios requires specialised methodological approaches that explicitly account for domain-specific challenges rather than relying on general-purpose solutions. The first part of this research tackles the long-standing challenge of accurate depth estimation for non-Lambertian surfaces that violate fundamental assumptions underlying traditional computer vision methods. A novel benchmarking framework and a learning-based approach are developed that enable robust geometric perception for optically complex materials through innovative training strategies and comprehensive evaluation methodologies. In the second part, the Thesis introduces methodological innovations that address fundamental limitations in existing unsupervised approaches for industrial anomaly detection and segmentation. Crossmodal feature mapping paradigms, test-time training strategies, and lightweight architectures are developed to enable practical deployment while achieving superior performance across diverse industrial inspection scenarios. Finally, the introduction of a comprehensive multiview multimodal benchmark reveals significant gaps in current algorithms while establishing an evaluation framework for future progress. Finally, in the third part, contemporary challenges posed by sophisticated diffusion-based manipulation techniques are addressed in the context of image forgery detection and localisation. Foundation model features are combined with multimodal information fusion strategies to achieve reliable identification of high-quality image manipulations, demonstrating how principles developed in anomaly detection can be adapted to distinguish authentic from manipulated digital content. The thesis unifies three research domains through shared methodological principles. Specialised learning consistently outperforms general approaches, with multimodal fusion and computational efficiency guiding robust, practical designs. Contributions include novel algorithms, datasets, training strategies, and evaluation frameworks, validated through extensive experiments establishing effectiveness and exposing future research.
Benchmarking Learnable Representations for Gigapixel Image Compression and Super-ResolutionIn Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), 2027
Neural Understanding of Objects and MaterialsAlma Mater Studiorum – University of Bologna, 2026
Modulate-and-Map: Crossmodal Feature Mapping with Cross-View Modulation for 3D Anomaly DetectionIn Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Findings, Jun 2026
Spectral Gating via Damped Oscillations for Adaptive Implicit Neural RepresentationsIn Computer Vision – ECCV 2026, Sep 2026Spotlight Oral
Learning to Be a Transformer to Pinpoint AnomaliesIEEE Access, Jun 2025
SiM3D: Single-instance Multiview Multimodal and Multisetup 3D Anomaly Detection BenchmarkIn Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), Oct 2025
Towards Reliable Identification of Diffusion-based Image ManipulationsIn Advances in Neural Information Processing Systems 38 (NeurIPS 2025), Dec 2025
Booster: A Benchmark for Depth From Images of Specular and Transparent SurfacesIEEE Transactions on Pattern Analysis and Machine Intelligence, Jan 2024
Test Time Training for Industrial Anomaly SegmentationIn Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, Jun 2024
Multimodal Industrial Anomaly Detection by Crossmodal Feature MappingIn Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Jun 2024
Learning Depth Estimation for Transparent and Mirror SurfacesIn Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), Oct 2023
Mitigating non-Lambertian surfaces issues in Stereo Matching with Neural Radiance FieldsAlma Mater Studiorum – University of Bologna, Jun 2022