Page Not Found
Page not found. Your pixels are in another canvas.
Sitemap
A list of all the posts and pages found on the site. For you robots out there is an XML version available for digesting as well.
Pages
About me
About me
Page not in menu
This is a page not in th emain menu
Posts
publications
Learning confidence measures in the wild
Authors: Fabio Tosi, Matteo Poggi, Alessio Tonioni, Luigi Di Stefano, & Stefano Mattoccia
Published in BMVC, 2017
In this paper we propose a methodology suited for training a confidence measure for stereo in a self-supervised manner.
Product recognition in store shelves as a sub-graph isomorphism problem
Authors: Alessio Tonioni and Luigi Di Stefano
Published in ICIAP, 2017
In this paper, we propose a computer vision pipeline to recognize products on shelves and verify compliance to the planned layout.
Unsupervised Adaptation For Deep Stereo
Authors: Alessio Tonioni, Matteo Poggi, stefano Mattoccia and Luigi Di Stefano
Published in ICCV, 2017
In this paper we propose a novel unsupervised adaptation approach that enables to fine-tune a deep learning stereo model without any ground-truth information.
Learning to detect good 3D keypoints
Authors: Alessio Tonioni, Samuele Salti, Federico Tombari, Riccardo Spezialetti and Luigi Di Stefano
Published in IJCV, 2018
In this paper we learn a descriptor-specific 3D keypoint detector so as to optimize the end-to-end performance of a feature matching pipeline
A deep learning pipeline for product recognition in store shelves
Authors: Alessio Tonioni, Eugenio Serra and Luigi Di Stefano.
Published in IPAS, 2018
In this paper, we propose a deep learning pipeline to recognize products on grocery shelves that can scale effortlessly to thousand of different products to recognize.
Exploiting Semantics in Adversarial Training for Image-Level Domain Adaptation
Authors: Pierluigi Zama Ramirez, Alessio Tonioni and Luigi Di Stefano
Published in IPAS, 2018
In this paper, we address the problem of domain adaptation for computer vision by learning a domain-to-domain image translation GAN. Peculiarly to our method, we introduce semantic constraints into the generation process to both avoid artifacts and guide the synthesis
Real-Time Highly Accurate Dense Depth on a Power Budget using an FPGA-CPU Hybrid SoC
Authors: Oscar Rahnama, Tommaso Cavallari, Stuart Golodetz, Alessio Tonioni, Thomas Joy, Luigi Di Stefano, Simon Walker, and Philip HS Torr
Published in IEEE Transactions on Circuits and Systems II: Express Briefs , 2019
In this paper, we leverage a FPGA-CPU chip to propose a novel, sophisticated, stereo approach that combines the best features of SGM and ELAS-based methods to compute highly accurate dense depth in real time.
Domain invariant hierarchical embedding for grocery products recognition
Authors: Alessio Tonioni and Luigi Di Stefano
Published in CVIU, 2019
In this paper we introduce a” deep learning architecture to effectively learn embedddings relying only on few samples and in presence of domain shifts.
Learning to Adapt for Stereo
Authors: Alessio Tonioni, Oscar Rahnama, Thomas Joy, Luigi Di Stefano, Thalaiyasingam Ajanthan, and Philip HS Torr.
Published in CVPR, 2019
In this paper we introduce a” learning-to-adapt” framework that enables deep stereo methods to continuously adapt to new target domains in an unsupervised manner.
Real-time self-adaptive deep stereo
Authors: Alessio Tonioni, Fabio Tosi, Matteo Poggi, Stefano Mattoccia and Luigi Di Stefano
Published in CVPR, 2019
In this paper we propose a real-time self adaptive deep stereo system.
Semi-Automatic Labeling for Deep Learning in Robotics
Authors: Daniele De Gregorio, Alessio Tonioni, Gianluca Palli and Luigi Di Stefano
Published in IEEE Transactions on Automation Science and Engineering , 2019
In this paper, we propose Augmented Reality Semi-automatic labeling (ARS), a semi-automatic method to create large labeled datasets with minimal human intervention
Learning Across Tasks and Domains
Authors: Pierluigi Zama Ramirez, Alessio Tonioni, Samuele Salti and Luigi Di Stefano
Published in ICCV, 2019
In this work, we introduce a novel adaptation framework that can operate across both task and domains.
Unsupervised Domain Adaptation for Depth Prediction from Images
Authors: Alessio Tonioni, Matteo Poggi, Stefano Mattoccia and Luigi Di Stefano
Published in TPAMI, 2019
In this paper we extend our previous unsupervised adaptation approach to fine-tune a deep learning stereo or mono model without any ground-truth information.
Continual Adaptation for Deep Stereo
Authors: Matteo Poggi, Alessio Tonioni, Fabio Tosi, Stefano Mattoccia and Luigi Di Stefano
Published in PAMI, 2020
In this paper we propose an etension of our real-time self adaptive deep stereo system.
A Divide et Impera Approach for 3D Shape Reconstruction from Multiple Views
Authors: Riccardo Spezialetti, David Joseph Tan, Alessio Tonioni, Keisuke Tateno and Federico Tombari
Published in 3DV, 2020
A deep learning pipeline for multi view reconstruction.
Unsupervised Novel View Synthesis from a Single Image
Authors: Pierluigi Zama Ramirez, Alessio Tonioni and Federico Tombari
Published in Arxive, 2021
An unsupervised approach for novel view synthesis.
LegoFormer: Transformers for Block-by-Block Multi-view 3D Reconstruction
Authors: Farid Yagubbayli, Alessio Tonioni and Federico Tombari
Published in Arxive, 2021
Transformers for voxel based 3D reconstruction.
ParGAN: Learning Real Parametrizable Transformations
Authors: Diego Martin Arroyo, Alessio Tonioni, Federico Tombari
Published in Arxive, 2022
Parametrizable CycleGAN.
LatentSwap3D: Semantic Edits on 3D Image GANs
Authors: Enis Simsar, Alessio Tonioni, Evin Pınar Örnek, Federico Tombari
Published in ICCV-W, 2022
Semantic edits in the latent space of Nerf based gan.
Learning Good Features to Transfer Across Tasks and Domains
Authors: Pierluigi Zama Ramirez, Adriano Cardace, Luca De Luigi, Alessio Tonioni, Samuele Salti, Luigi Di Stefano
Published in PAMI, 2023
In this work, we extend an adaptation framework that can operate across both task and domains.
Batch Normalization Embeddings for Deep Domain Generalization
Authors: Mattia Segù, Alessio Tonioni and Federico Tombari
Published in PR, 2023
An embedding based approach for deep domain generalization.
NeRF-GAN Distillation for Efficient 3D-Aware Generation with Convolutions
Authors: Mohamad Shahbazi, Evangelos Ntavelis, Alessio Tonioni, Edo Collins, Danda Pani Paudel, Martin Danelljan, Luc Van Gool
Published in ICCV-W, 2023
StyleGan like network can approximate NerfGAN.
NeRF-Supervised Deep Stereo
Authors: Fabio Tosi, Alessio Tonioni, Daniele De Gregorio, Matteo Poggi
Published in CVPR, 2023
NeRF makes great groundtruth for stereo systems.
TextMesh: Generation of Realistic 3D Meshes From Text Prompts
Authors: Christina Tsalicoglou, Fabian Manhardt, Alessio Tonioni, Michael Niemeyer, Federico Tombari
Published in 3DV, 2023
Turning Tetx prompt into full 3D meshes
TouchSDF: A DeepSDF Approach for 3D Shape Reconstruction using Vision-Based Tactile Sensing
Authors: Mauro Comi, Yijiong Lin, Alex Church, Alessio Tonioni, Laurence Aitchison, Nathan F Lepora
Published in RAL, 2023
Touch sensors meet 3D computer vision
LIME: Localized Image Editing via Attention Regularization in Diffusion Models
Authors: Enis Simsar, Alessio Tonioni, Yongqin Xian, Thomas Hofmann, Federico Tombari
Published in WACV, 2023
Attenton modulation is all you need for precise image editing
Text-Conditioned Resampler For Long Form Video Understanding
Authors: Bruno Korbar, Yongqin Xian, Alessio Tonioni, Andrew Zisserman, Federico Tombari
Published in ECCV, 2023
Let large language models see videos
InseRF: Text-Driven Generative Object Insertion in Neural 3D Scenes
Authors: Mohamad Shahbazi, Liesbeth Claessens, Michael Niemeyer, Edo Collins, Alessio Tonioni, Luc Van Gool, Federico Tombari
Published in Arxive, 2024
Adding 3D objects in scenes out of tin air
Snap-it, Tap-it, Splat-it: Tactile-Informed 3D Gaussian Splatting for Reconstructing Challenging Surfaces
Authors: Mauro Comi, Alessio Tonioni, Max Yang, Jonathan Tremblay, Valts Blukis, Yijiong Lin, Nathan F Lepora, Laurence Aitchison
Published in 3DV, 2024
Touch meet vision for 3D reconstrunction
BRAVE: Broadening the visual encoding of vision-language models
Authors: Oğuzhan Fatih Kar, Alessio Tonioni, Petra Poklukar, Achin Kulshrestha, Amir Zamir, Federico Tombari
Published in ECCV, 2024
Ensembling for LMM
Active data curation effectively distills large-scale multimodal models
Authors: Vishaal Udandarao, Nikhil Parthasarathy, Muhammad Ferjad Naeem, Talfan Evans, Samuel Albanie, Federico Tombari, Yongqin Xian, Alessio Tonioni, Olivier J Hénaff
Published in CVPR, 2024
Active Data Curation beats Distillation
UIP2P: Unsupervised Instruction-based Image Editing via Cycle Edit Consistency
Authors: Enis Simsar, Alessio Tonioni, Yongqin Xian, Thomas Hofmann, Federico Tombari
Published in ICCV, 2024
Unsupervised IP2P
Omnia de EgoTempo: Benchmarking Temporal Understanding of Multi-Modal LLMs in Egocentric Videos
Authors: Chiara Plizzari, Alessio Tonioni, Yongqin Xian, Achin Kulshrestha, Federico Tombari
Published in CVPR, 2025
New Egocentric video benchmark
Zero-Shot Styled Text Image Generation, but Make It Autoregressive
Authors: Vittorio Pippi, Fabio Quattrini, Silvia Cascianelli, Alessio Tonioni, Rita Cucchiara
Published in CVPR, 2025
Autoregressive handwriting generation
Test-Time Visual In-Context Tuning
Authors: Jiahao Xie, Alessio Tonioni, Nathalie Rauschmayr, Federico Tombari, Bernt Schiele
Published in CVPR, 2025
test time cycle
Training-free Online Video Step Grounding
Authors: Luca Zanella, Massimiliano Mancini, Yiming Wang, Alessio Tonioni, Elisa Ricci
Published in Neurips, 2025
Online video step grounding
Autoregressive Styled Text Image Generation, but Make it Reliable
Authors: Carmine Zaccagnino, Fabio Quattrini, Vittorio Pippi, Silvia Cascianelli, Alessio Tonioni, Rita Cucchiara
Published in WACV, 2025
Better autoregressive handwriting generation
RefAM: Attention Magnets for Zero-Shot Referral Segmentation
Authors: Anna Kukleva, Enis Simsar, Alessio Tonioni, Muhammad Ferjad Naeem, Federico Tombari, Jan Eric Lenssen, Bernt Schiele
Published in ArXiv, 2026
Most existing approaches to referring segmentation achieve strong performance only through fine-tuning or by composing multiple pre-trained models, of…
MOSAIC-GS: Monocular Scene Reconstruction via Advanced Initialization for Complex Dynamic Environments
Authors: Svitlana Morkva, Michael Oechsle, Alessio Tonioni, Marco Hutter, Vaishakh Patil
Published in CVPR, 2026
We present MOSAIC-GS, a novel, fully explicit, and computationally efficient approach for high-fidelity dynamic scene reconstruction from monocular vi…
Shifting the Breaking Point of Flow Matching for Multi-Instance Editing
Authors: Carmine Zaccagnino, Fabio Quattrini, Enis Simsar, Marta Tintoré Gazulla, Rita Cucchiara, Alessio Tonioni, Silvia Cascianelli
Published in ICML, 2026
Flow matching models have recently emerged as an efficient alternative to diffusion, especially for text-guided image generation and editing, offering…
R-CoV: Region-Aware Chain-of-Verification for Alleviating Object Hallucinations in LVLMs
Authors: Jiahao Xie, Alessio Tonioni, Nathalie Rauschmayr, Federico Tombari, Bernt Schiele
Published in ArXiv, 2026
Large vision-language models (LVLMs) have demonstrated impressive performance in various multimodal understanding and reasoning tasks. However, they s…
SSL-R1: Self-Supervised Visual Reinforcement Post-Training for Multimodal Large Language Models
Authors: Jiahao Xie, Alessio Tonioni, Nathalie Rauschmayr, Federico Tombari, Bernt Schiele
Published in ArXiv, 2026
Reinforcement learning (RL) with verifiable rewards (RLVR) has demonstrated the great potential of enhancing the reasoning abilities in multimodal lar…
FullFlow: Upgrading Text-to-Image Flow Matching Models for Bidirectional Vision–Language Generation
Authors: Eric Tillmann Bill, Enis Simsar, Alessio Tonioni, Thomas Hofmann
Published in ArXiv, 2026
Modern text-to-image diffusion models encode rich visual priors, but expose them only through one-way text-conditioned generation. Existing unified vi…
PARCEL: Pool-Anchored Resampling with Conditioned Elastic Queries for Efficient Vision-Language Understanding
Authors: Selim Kuzucu, Alessio Tonioni, Vasile Lup, Bernt Schiele, Federico Tombari, Muhammad Ferjad Naeem
Published in ArXiv, 2026
Large Vision-Language Models (LVLMs) map visual inputs into dense token sequences, imposing a quadratic computational bottleneck for inference. Elasti…
DataComp-VLM: Improved Open Datasets for Vision-Language Models
Authors: Matteo Farina, Vishaal Udandarao, Thao Nguyen, Selim Kuzucu, Maximilian Böther, Andreas Hochlehnert, Adhiraj Ghosh, Marianna Nezhurina, Karsten Roth, Joschka Struber, Yuhui Zhang, Sebastian Dziadzio, Elaine Sui, Soumya Jahagirdar, Dhruba Ghosh, Hasan Hammoud, Thomas De Min, Simone Caldarella, Jehanzeb Mirza, Sedrick Keh, Mehdi Cherti, Hilde Kuehne, Bernt Schiele, Serena Yeung-Levy, Muhammad Ferjad Naeem, Federico Tombari, Ana Klimovic, Elisa Ricci, Matthias Bethge, Sewoong Oh, Ameya Prabhu, Alessio Tonioni, Jenia Jitsev, Massimiliano Mancini, Ludwig Schmidt, Nikhil Parthasarathy
Published in ArXiv, 2026
Building performant Vision-Language Models (VLMs) requires carefully curating large-scale training datasets, yet the community lacks systematic benchm…
Editing Everything Everywhere All at Once
Authors: Fabio Quattrini, Carmine Zaccagnino, Enis Simsar, Marta Tintoré Gazulla, Rita Cucchiara, Alessio Tonioni, Silvia Cascianelli
Published in ArXiv, 2026
Editing multiple elements of an image in a single forward pass is a practical alternative to multi-turn image manipulation, offering improved efficien…
teaching
Academic Tutor
Undergraduate course, University of Bologna, computer engineering course, 2019
I have been academic tutor for the courses:
- Computer Vision and Image Processing M - 2016/2017
- Computer Vision and Image Processing M - 2017/2018
- Reti Logiche T - 2019/2020
Corporate Trainer
Corporate Training Course, Fondazione Aldini Valeriani, 2019
Corporate Trainer for Fondazione Aldini Valeriani on Machine-Deep Learning.