-
Paper accepted in IEEE TMM
Our paper “Security and Real-time FPGA integration for Learned Image Compression” has been accepted in IEEE Transactions on Multimedia. An open-access version is available here. Authors: Alaa Eddine, Mazouz; Telecom Paris, COMELECDe Sousa Trias, Carl ; TELECOM SudParis, SAMOVARChaudhuri, Suamnta; Telecom Paris, COMELEC, SSH TeamFiandrotti, Attilio; UNITO, Dipartimento di InformaticaCagnazzo, Marco; Università degli Studi di
-
Paper accepted in IEEE TCSVT
Our paper “Compression in 3D Gaussian Splatting: A Survey of Methods, Trends, and Future Directions” has been accepted in IEEE Transactions on Circuits and Systems for Video Technology. This work has been carried out in collaboration with the colleagues at Telecom-Paris, Università di Torino, CentraleSupéléc, Kyung Hee University, and University of Electronic Science and Technology
-
New paper accepted @ IEEE ToB
Our paper “SalFormer360: A Transformer-Based Saliency Estimation Model for 360-Degree Videos” has been recently published in IEEE Transactions on Broadcasting. We propose a new method for saliency estimation of 360-degree videos built on a transformer-based architecture. Our approach is based on the combination of an existing encoder architecture, SegFormer, and a custom decoder. The SegFormer
-
New paper accepted!
Our paper “Quality assessment of 3D reconstructed meshes: Bridging objective metrics, subjective perception, and behavioral cues” has been accepted for publication in Signal Processing: Image Communication!
-
New EURASIP Student Committee member
Annalisa Gallina has been appointed as EURASIP Student Committee representative for the Technical Area Committee on Visual Information Processing.
-
Two journal papers accepted
Two papers have been accepted for publication in Signal Processing: Image Communication!
-
MEDIALAB @RESTART plenary meeting
19-21 January 2026 RESTART Final Plenary Dissemination Event
-
Paper accepted at ICCV 2025
We are pleased to announce that the paper “LoRA.rar: Learning to Merge LoRAs via Hypernetworks for Subject-Style Conditioned Image Generation” has been accepted at the IEEE/CVF International Conference on Computer Vision (ICCV). This work is the latest successful result of our collaboration with the Samsung R&D Institute UK (SRUK). Congratulations to the authors Donald Shenaj,
-
Paper accepted @ CVPR 2025
We are pleased to announce that the paper “MultimodalStudio: A Heterogeneous Sensor Dataset and Framework for Neural Rendering across Multiple Imaging Modalities” has been accepted at the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) held in Nashville, Tennessee. This work is the latest successful result of our long-lasting collaboration with the Stuttgart Technology
-
3 MEDIALAB papers @ ECCV
We will present 3 papers (2 at the main conference and a workshop one) at the European Conference on Computer Vision (ECCV) : “HoloADMM: High-Quality Holographic Complex Field Recovery” (in collaboration with Sony Europe) and “Learning from the Web: Language Drives Weakly-Supervised Incremental Learning for Semantic Segmentation” (in collaboration with the Xidian University) at the
