Learning confidence measures in the wild
Tosi, F., Poggi, M., Tonioni, A., Di Stefano, L., & Mattoccia, S. (2017, September). Learning confidence measures in the wild. In 28th British Machine Vision Conference (BMVC 2017) (Vol. 2, No. 4).
CV
Education
- B.S. in Computer Engineering, University of Bologna, 2013
- M.S. in Computer Engineering, University of Bologna, 2015
- Ph.D in Computer Science and Engineering, University of Bologna, 2019
Work experience
- Dec. 2020 - Present: Research Scientist
- Google Zurich
- Research Group: Federico Tombari
- Jul. 2019 - Dec. 2020: Visiting Researcher
- Google Zurich
- Research Group: Federico Tombari
- Jan. 2019 - Jun. 2019: Post-doc researcher
- CVLAB, University of Bologna
- Supervisor: Luigi Di Stefano
- May 2018 - Nov. 2018: Visiting Ph.D student
- TVG group, University of Oxford
- Supervisor: Philip Torr
Publications
Product recognition in store shelves as a sub-graph isomorphism problem
Tonioni, A., & Di Stefano, L. (2017, September). Product recognition in store shelves as a sub-graph isomorphism problem. In International Conference on Image Analysis and Processing (pp. 682-693). Springer, Cham.
Unsupervised Adaptation For Deep Stereo
Tonioni, A., Poggi, M., Mattoccia, S., & Di Stefano, L. (2017). Unsupervised adaptation for deep stereo. In Proceedings of the IEEE International Conference on Computer Vision (pp. 1605-1613).
Learning to detect good 3D keypoints
Tonioni, A., Salti, S., Tombari, F., Spezialetti, R., & Di Stefano, L. (2018). Learning to detect good 3D keypoints. International Journal of Computer Vision, 126(1), 1-20.
A deep learning pipeline for product recognition in store shelves
Tonioni, Alessio, Eugenio Serra, and Luigi Di Stefano. "A deep learning pipeline for product recognition in store shelves." In International Conference on Image Processing, Applications and Systems, 2018
Exploiting Semantics in Adversarial Training for Image-Level Domain Adaptation
Ramirez, Pierluigi Zama, Alessio Tonioni, and Luigi Di Stefano. "Exploiting Semantics in Adversarial Training for Image-Level Domain Adaptation." In International Conference on Image Processing, Applications and Systems, 2018
Real-Time Highly Accurate Dense Depth on a Power Budget using an FPGA-CPU Hybrid SoC
Rahnama, Oscar, Tommaso Cavallari, Stuart Golodetz, Alessio Tonioni, Thomas Joy, Luigi Di Stefano, Simon Walker, and Philip HS Torr, "Real-Time Highly Accurate Dense Depth on a Power Budget using an FPGA-CPU Hybrid SoC," in IEEE Transactions on Circuits and Systems II: Express Briefs.
Domain invariant hierarchical embedding for grocery products recognition
Tonioni, Alessio, and Luigi Di Stefano. "Domain invariant hierarchical embedding for grocery products recognition." Computer Vision and Image Understanding (2019).
Learning to Adapt for Stereo
Tonioni, Alessio, Oscar Rahnama, Thomas Joy, Luigi Di Stefano, Thalaiyasingam Ajanthan, and Philip HS Torr. "Learning to Adapt for Stereo." The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2019
Real-time self-adaptive deep stereo
Tonioni, A., Tosi, F., Poggi, M., Mattoccia, S., & Di Stefano, L. (2019). The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2019
Semi-Automatic Labeling for Deep Learning in Robotics
Daniele De Gregorio, Alessio Tonioni, Gianluca Palli and Luigi Di Stefano, "Semi-Automatic Labeling for Deep Learning in Robotics," in IEEE Transactions on Automation Science and Engineering.
Learning Across Tasks and Domains
Ramirez, P. Z., Tonioni, A., Salti, S., & Di Stefano, L. (2019). Learning Across Tasks and Domains. arXiv preprint arXiv:1904.04744.
Unsupervised Domain Adaptation for Depth Prediction from Images
Tonioni, A., Poggi, M., Mattoccia, S., & Di Stefano, L. (2019). Unsupervised Domain Adaptation for Depth Prediction from Images. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2019
Continual Adaptation for Deep Stereo
Poggi, M., Tonioni, A., Tosi, F., Mattoccia, S., & Di Stefano, L. (2019). IEEE Transactions on Pattern Analysis and Machine Intelligence, 2020
A Divide et Impera Approach for 3D Shape Reconstruction from Multiple Views
Spezialetti, R., Tan, D.J., Tonioni, A., Tateno, K. and Tombari, F., 2020. A Divide et Impera Approach for 3D Shape Reconstruction from Multiple Views. 3DV20.
Unsupervised Novel View Synthesis from a Single Image
Zama Ramirez, Pierluigi, Alessio Tonioni, and Federico Tombari. "Unsupervised Novel View Synthesis from a Single Image." arXiv preprint arXiv:2102.03285 (2021).
LegoFormer: Transformers for Block-by-Block Multi-view 3D Reconstruction
Yagubbayli, Farid, Alessio Tonioni, and Federico Tombari. "LegoFormer: Transformers for Block-by-Block Multi-view 3D Reconstruction." arXiv preprint arXiv:2106.12102 (2021).
ParGAN: Learning Real Parametrizable Transformations
Arroyo, Diego Martin, Alessio Tonioni, and Federico Tombari. "ParGAN: Learning Real Parametrizable Transformations." arXiv preprint arXiv:2211.04996 (2022).
LatentSwap3D: Semantic Edits on 3D Image GANs
Simsar, Enis, et al. "LatentSwap3D: Semantic Edits on 3D Image GANs." arXiv preprint arXiv:2212.01381 (2022).
Learning Good Features to Transfer Across Tasks and Domains
Ramirez, Pierluigi Zama, et al. "Learning Good Features to Transfer Across Tasks and Domains." IEEE Transactions on Pattern Analysis and Machine Intelligence (2023).
Batch Normalization Embeddings for Deep Domain Generalization
Segu, Mattia, Alessio Tonioni, and Federico Tombari. "Batch normalization embeddings for deep domain generalization." Pattern Recognition 135 (2023): 109115.
NeRF-GAN Distillation for Efficient 3D-Aware Generation with Convolutions
Shahbazi, Mohamad, et al. "NeRF-GAN Distillation for Efficient 3D-Aware Generation with Convolutions." arXiv preprint arXiv:2303.12865 (2023).
NeRF-Supervised Deep Stereo
Tosi, Fabio, et al. "NeRF-Supervised Deep Stereo." arXiv preprint arXiv:2303.17603 (2023).
TextMesh: Generation of Realistic 3D Meshes From Text Prompts
Tsalicoglou, Christina, et al. "TextMesh: Generation of Realistic 3D Meshes From Text Prompts." arXiv preprint arXiv:2304.12439 (2023).
TouchSDF: A DeepSDF Approach for 3D Shape Reconstruction using Vision-Based Tactile Sensing
Comi, Mauro, et al. "Touchsdf: A deepsdf approach for 3d shape reconstruction using vision-based tactile sensing." IEEE Robotics and Automation Letters (2024).
LIME: Localized Image Editing via Attention Regularization in Diffusion Models
Simsar, Enis, et al. "LIME: Localized Image Editing via Attention Regularization in Diffusion Models." arXiv preprint arXiv:2312.09256 (2023).
Text-Conditioned Resampler For Long Form Video Understanding
Korbar, Bruno, et al. "Text-Conditioned Resampler For Long Form Video Understanding." arXiv preprint arXiv:2312.11897 (2023).
InseRF: Text-Driven Generative Object Insertion in Neural 3D Scenes
Shahbazi, Mohamad, et al. "InseRF: Text-Driven Generative Object Insertion in Neural 3D Scenes." arXiv preprint arXiv:2401.05335 (2024).
Snap-it, Tap-it, Splat-it: Tactile-Informed 3D Gaussian Splatting for Reconstructing Challenging Surfaces
Comi, Mauro, et al. "Snap-it, Tap-it, Splat-it: Tactile-Informed 3D Gaussian Splatting for Reconstructing Challenging Surfaces." arXiv preprint arXiv:2403.20275 (2024).
BRAVE: Broadening the visual encoding of vision-language models
Kar, Oğuzhan Fatih, et al. "BRAVE: Broadening the visual encoding of vision-language models." arXiv preprint arXiv:2404.07204 (2024).
Talks
Deep Learning For Computer Vision
Talk at Scuderia - FF Urban CooLab, Bologna, Italy
Real-time self-adaptive deep stereo
Talk at British Computer Society BCS, 5 Southampton St, London WC2E 7HA