Stefano Petrangeli

Stefano is a Senior Research Scientist in the REAL Lab in Adobe Research. His current research work is primarily on (i) creating LLM-based AI Assistants to make content creation and editing faster and more accessible, leveraging planning & reasoning techniques, (2) improving content using behavioral data analytics.

Stefano obtained his Ph.D. in Computer Science Engineering in 2018 from Ghent University (Belgium), where he focused on the optimal delivery of adaptive video streaming services. During his Ph.D., he interned in Adobe where he worked on 360-degree VR video streaming.

Google scholar page

AI & Machine Learning Content Intelligence Intelligent Agents & Assistants

Publications

December 6, 2025 ACM International Conference on Multimedia in Asia (MM Asia)

Power Efficient Mobile VTuber Live Streaming

Stefano Petrangeli, Vishy Swaminathan

AR, VR & 360 Photography Computer Vision, Imaging & Video

August 3, 2025 ACL 2025

VISIAR: Empower MLLM for Visual Story Ideation

zhaoyang xia, Somdeb Sarkhel, Mehrab Tanjim, Stefano Petrangeli, Ishita Dasgupta, Saayan Mitra

Intelligent Agents & Assistants

July 3, 2025 ICME 2025

SmartEdit: Editing-driven Engagement Prediction and Enhancement of Short-Videos

saumya gupta, Ishita Dasgupta, Stefano Petrangeli, Somdeb Sarkhel

Content Intelligence Intelligent Agents & Assistants

April 26, 2025 Consolidated Health Informatics (CHI)

DepthScape: Authoring 2.5D Designs with Depth Estimation

Cuong Nguyen, Yu Shen, Stefano Petrangeli, Matheus Gadelha

Graphics (2D & 3D) Human Computer Interaction Intelligent Agents & Assistants

December 14, 2024 Neural Information Processing Systems (NeurIPS)

Copiloting Creative 3D Scene Modeling and Visualization with Generative Agents

Stefano Petrangeli, Yu Shen, Gang Wu, Matheus Gadelha, Cuong Nguyen, Petrangeli

AI & Machine Learning AR, VR & 360 Photography Intelligent Agents & Assistants

May 7, 2024 International Conference on Learning Representations (ICLR), 2024

Large Content And Behavior Models To Understand, Simulate, And Optimize Content And Behavior

Ashmit Khandelwal, Aditya Agrawal, Aanisha Bhattacharyya, Yaman K Singla, Somesh Singh, Uttaran Bhattacharya, Ishita Dasgupta, Stefano Petrangeli, Rajiv Ratn Shah, Changyou Chen, Balaji Krishnamurthy

AI & Machine Learning Content Intelligence Data Intelligence

April 15, 2024 ACM Multimedia Systems Conference (MMSys)

Integrating Content Authenticity with DASH Video Streaming

Stefano Petrangeli, Haoliang Wang, Maurice Fisher, Dave Kozma, Massy Mahamli, Pia Blumenthal, Andy Parsons

Computer Vision, Imaging & Video

December 11, 2023 ISM 2023

Active Context Modeling for Efficient Image and Burst Compression

Yang Li, Gang Wu, Stefano Petrangeli, Haoliang Wang, Ryan A. Rossi, Vishy Swaminathan

AI & Machine Learning Computer Vision, Imaging & Video

December 11, 2023 ISM 2023

GPU-accelerated Lossless Image Compression with Massive Parallelization

Yu Shen, Gang Wu, Vishy Swaminathan, Haoliang Wang, Stefano Petrangeli, Tong Yu

AI & Machine Learning Computer Vision, Imaging & Video

December 11, 2023 IEEE International Symposium on Multimedia (ISM)

Active Context Modeling for Efficient Image and Burst Compression

Yang Li, Gang Wu, Stefano Petrangeli, Haoliang Wang, Ryan A. Rossi, Vishy Swaminathan

AI & Machine Learning Computer Vision, Imaging & Video

December 11, 2023 IEEE International Symposium on Multimedia (ISM)

GPU-accelerated Lossless Image Compression with Massive Parallelization

Yu Shen, Gang Wu, Vishy Swaminathan, Haoliang Wang, Stefano Petrangeli, Tong Yu

Computer Vision, Imaging & Video Systems & Languages

December 11, 2023 IEEE International Symposium on Multimedia (ISM)

EHT-SR: An Entropy-Based Hybrid Approach for Faster Super-Resolution

Stefano Petrangeli

AI & Machine Learning Computer Vision, Imaging & Video

December 11, 2023 IEEE International Symposium on Multimedia (ISM)

Content-aware Progressive Image Compression and Syncing

Junda Wu, Haoliang Wang, Tong Yu, Handong Zhao, Gang Wu, Stefano Petrangeli, Sungchul Kim, Vishy Swaminathan

AI & Machine Learning Computer Vision, Imaging & Video

October 2, 2023 International Conference on Computer Vision (ICCV)

VADER: Video Alignment Differencing and Retrieval

Alex Black, Simon Jenni, Tu Bui, Mehrab Tanjim, Stefano Petrangeli, Ritwik Sinha, Vishy Swaminathan

AI & Machine Learning Content Intelligence

January 3, 2023 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)

Recipe2Video: Synthesizing Personalized Videos from Recipe Texts

Prateksha Udhayanan, Suryateja BV, Parth Laturia, Dev Chauhan, Darshan Khandelwal, Stefano Petrangeli, Balaji Vasan Srinivasan

Computer Vision, Imaging & Video Document Intelligence

December 13, 2022 The ACM International Conference on Multimedia in Asia (MMAsia)

A reality check of positioning in multiuser mobile augmented reality: Measurement and analysis

Na Wang, Haoliang Wang, Stefano Petrangeli, Vishy Swaminathan, Fei Li, Songqing Chen

AR, VR & 360 Photography

December 5, 2022 IEEE International Symposium on Multimedia (ISM)

Task-Oriented Near-Lossless Burst Compression

Weixin Jiang, Gang Wu, Vishy Swaminathan, Stefano Petrangeli, Haoliang Wang, Ryan A. Rossi, Nedim Lipka

AI & Machine Learning Computer Vision, Imaging & Video

December 5, 2022 IEEE International Symposium on Multimedia (ISM)

Towards Accurate Positioning in Multiuser Augmented Reality on Mobile Devices

Na Wang, Haoliang Wang, Stefano Petrangeli, Vishy Swaminathan, Fei Li, Songqing Chen

AR, VR & 360 Photography

December 5, 2022 IEEE International Symposium on Multimedia (ISM)

Contextualized Styling of Images for Web Interfaces using Reinforcement Learning

Pooja Guhan, Saayan Mitra, Somdeb Sarkhel, Stefano Petrangeli, Ritwik Sinha, Vishy Swaminathan, Aniket Bera, Dinesh Manocha

AI & Machine Learning Content Intelligence

October 10, 2022 ACM International Conference on Multimedia (ACMMM), 2022

Show Me What I Like: Detecting User-Specific Video Highlights Using Content-Based Multi-Head Attention

Uttaran Bhattacharya, Gang Wu, Stefano Petrangeli, Vishy Swaminathan, Dinesh Manocha

AI & Machine Learning Computer Vision, Imaging & Video Content Intelligence

January 8, 2022 IEEE VR

Instant Reality: Gaze-Contingent Perceptual Optimization for 3D Virtual Reality Streaming

Shaoyu Chen, Budmonde Duinkharjav, Xin Sun, Li-Yi Wei, Stefano Petrangeli, Jose Echevarria, Claudio Silva, Qi Sun

AR, VR & 360 Photography

October 10, 2021 IEEE/CVF International Conference on Computer Vision (ICCV), 2021

HighlightMe: Detecting Highlights From Human-Centric Videos

Uttaran Bhattacharya, Gang Wu, Stefano Petrangeli, Vishy Swaminathan, Dinesh Manocha

AI & Machine Learning Computer Vision, Imaging & Video Content Intelligence

June 8, 2020 ACM International Workshop on Immersive Mixed and Virtual Environment Systems (MMVE)

Towards field-of-view prediction for augmented reality applications on mobile devices

Na Wang, Haoliang Wang, Stefano Petrangeli, Vishy Swaminathan, Fei Li, Songqing Chen

AI & Machine Learning AR, VR & 360 Photography

December 9, 2019 Proceedings of IEEE International Symposium on Multimedia (IEEE ISM)

Dynamic Adaptive Streaming for Augmented Reality Applications

Stefano Petrangeli, Gwendal Simon, Haoliang Wang, Vishy Swaminathan

Computer Vision, Imaging & Video Graphics (2D & 3D)

November 30, 2019 ACM Transactions on Multimedia Computing, Communications, and Applications (TOMM)

Tile-Based Adaptive Streaming for Virtual Reality Video

Jeroen van der Hooft, Maria Torres Vega, Stefano Petrangeli, Tim Wauters, Filip De Turck

Computer Vision, Imaging & Video

November 30, 2019 ACM Transactions on Multimedia Computing, Communications, and Applications (TOMM)

Dissecting the Performance of VR Video Streaming Through the VR-EXP Experimentation Platform

Roberto Iraja Tavares Da Costa Filho, Marcelo Caggiani Luizelli, Stefano Petrangeli, Maria Torres Vega, Jeroen van der Hooft, Tim Wauters, Filip De Turck, Luciano Paschoal Gaspary

Computer Vision, Imaging & Video

June 18, 2019 Proceedings of ACM Multimedia Systems Conference (ACM MMSys)

Exploring New York in 8K: an adaptive tile-based virtual reality video streaming experience

Maria Torres Vega, Jeroen van der Hooft, Joris Heyse, Femke De Backere, Tim Wauters, Filip De Turck, Stefano Petrangeli

Best demo award

Computer Vision, Imaging & Video

April 8, 2019 Proceedings of IEEE International Symposium on Integrated Network Management (IEEE IM)

Optimizing Adaptive Tile-Based Virtual Reality Video Streaming

Jeroen van der Hooft, Maria Torres Vega, Stefano Petrangeli, Tim Wauters, Filip De Turck

Computer Vision, Imaging & Video

April 8, 2019 Proceedings of IEEE International Symposium on Integrated Network Management (IEEE IM)

QoE-Centric Network-Assisted Delivery of Adaptive Video Streaming Services

Stefano Petrangeli, Tim Wauters, Filip De Turck

AI & Machine Learning Computer Vision, Imaging & Video

March 23, 2019 Proceedings of IEEE Conference on Virtual Reality and 3D User Interfaces (IEEE VR)

Streaming a Sequence of Textures for Adaptive 3D Scene Delivery

Gwendal Simon, Stefano Petrangeli, Nathan Carr, Vishy Swaminathan

Computer Vision, Imaging & Video Graphics (2D & 3D)

February 19, 2019 Proceedings of International Workshop on Quality of Experience Management

Quality Assessment for Adaptive Virtual Reality Video Streaming: A Probabilistic Approach on the User’s Gaze

Jeroen van der Hooft, Maria Torres Vega, Stefano Petrangeli, Tim Wauters, Filip De Turck

Computer Vision, Imaging & Video

December 10, 2018 Proceedings of IEEE International Conference on Artificial Intelligence and Virtual Reality (IEEE AIVR)

Trajectory-Based Viewport Prediction for 360-Degree Virtual Reality Videos

Stefano Petrangeli, Gwendal Simon, Vishy Swaminathan

AI & Machine Learning Computer Vision, Imaging & Video

August 11, 2018 Multimedia Tools and Applications (MTA)

A scalable WebRTC-based framework for remote video collaboration applications

Stefano Petrangeli, Dries Pauwels, Jeroen van der Hooft, Matúš Žiak, Jürgen Slowack, Tim Wauters, Fillip De Turck

Computer Vision, Imaging & Video

August 3, 2018 IEEE Access

Performance Characterization of Low-Latency Adaptive Streaming From Video Portals

Jeroen van der Hooft, Cedric De Boom, Stefano Petrangeli, Tim Wauters, Filip De Turck

AI & Machine Learning Computer Vision, Imaging & Video

June 12, 2018 Proceedings of ACM Multimedia Systems Conference (ACM MMSys)

Low-latency delivery of news-based video content

Jeroen van der Hooft, Dries Pauwels, Cedric De Boom, Stefano Petrangeli, Tim Wauters, Filip De Turck

Computer Vision, Imaging & Video

June 12, 2018 Proceedings of ACM Multimedia Systems Conference (ACM MMSys)

Improving quality and scalability of webRTC video collaboration applications

Stefano Petrangeli, Dries Pauwels, Jeroen van der Hooft, Tim Wauters, Filip De Turck, Jürgen Slowack

Computer Vision, Imaging & Video

June 12, 2018 Proceedings of ACM Multimedia Systems Conference (ACM MMSys)

Predicting the performance of virtual reality video streaming in mobile networks

Roberto Irajá Tavares da Costa Filho, Marcelo Caggiani Luizelli, Maria Torres Vega, Jeroen van der Hooft, Stefano Petrangeli, Tim Wauters, Filip De Turck, Luciano Paschoal Gaspary

AI & Machine Learning Computer Vision, Imaging & Video

May 31, 2018 ACM Transactions on Multimedia Computing, Communications, and Applications (TOMM)

Quality of Experience-Centric Management of Adaptive Video Streaming Services: Status and Challenges

Stefano Petrangeli, Jeroen Van Der Hooft, Tim Wauters, Tim Wauters

Computer Vision, Imaging & Video

News

From intern to mentor: How former Adobe Research interns welcome the next generation

Each summer, mentors and interns join forces at Adobe Research. Mentors offer guidance as interns experience life in an industry research lab and dive deep into their projects. Learn more about how former Adobe Research interns welcome the next generation!

January 13, 2022