Manel Baradad

Manel Baradad

manelbaradad@gmail.com

About me

I am Manel Baradad Jurjo, PhD from MIT (September 2024) under the supervision of Prof. Antonio Torralba. I currently work as an Applied Scientist at Amazon. My research spans image generation and representation learning, with past work in 3D scene understanding and computational photography. Before coming to MIT, I did my undergrad at CFIS-UPC, where I was fortunate to work in the Image Processing Group under the supervision of Prof. Xavier Giró-i-Nieto.

You can contact me at: manelbaradad@gmail.com.

Publications

PLACID: Identity-Preserving Multi-Object Compositing via Video Diffusion with Synthetic Trajectories

Gemma Canet Tarrés, Manel Baradad, Francesc Moreno-Noguer, Yumeng Li

CVPR 2026

[paper] [webpage]

Separating Knowledge and Perception with Procedural Data

Adrián Rodríguez-Muñoz, Manel Baradad, Phillip Isola, Antonio Torralba

ICML 2025

[paper] [code]

A Vision Check-up for Language Models

Pratyusha Sharma*, Tamar Rott Shaham*, Manel Baradad, Stephanie Fu, Adrián Rodríguez-Muñoz, Shivam Duggal, Phillip Isola, Antonio Torralba

CVPR 2024

[paper] [webpage]

Background Prompting for Improved Object Depth

Manel Baradad, Yuanzhen Li, Forrester Cole, Michael Rubinstein, Antonio Torralba, William T. Freeman, Varun Jampani

arxiv 2023

[paper] [webpage] [code]

Deep Augmentation: Enhancing Self-Supervised Learning through Transformations in Higher Activation Space

Rickard Brüel-Gabrielsson, Tongzhou Wang, Manel Baradad, Justin Solomon

arxiv 2023

[paper]

Procedural Image Programs for Representation Learning

Manel Baradad, Chun-Fu (Richard) Chen, Jonas Wulff, Tongzhou Wang, Rogerio Feris, Antonio Torralba, Phillip Isola

NeurIPS 2022

[paper] [webpage] [code]

Learning to See by Looking at Noise

Manel Baradad*, Jonas Wulff*, Tongzhou Wang, Phillip Isola, Antonio Torralba

NeurIPS 2021 (Spotlight)

[paper] [webpage] [code]

Height and Uprightness Invariance for 3D Prediction From a Single View

Manel Baradad, Antonio Torralba

CVPR 2020

[paper] [code] [video]

Using Unknown Occluders to Recover Hidden Scenes

Adam B. Yedidia, Manel Baradad, Christos Thrampoulidis, William T. Freeman, Gregory W. Wornell

CVPR 2019

[paper]

Inferring Light Fields From Shadows

Manel Baradad, Vickie Ye, Adam B. Yedidia, Fredo Durand, William T. Freeman, Gregory W. Wornell, Antonio Torralba

CVPR 2018 (Spotlight)

[paper] [code] [video]

Recurrent Neural Networks for Semantic Instance Segmentation

Amaia Salvador, Miriam Bellver, Victor Campos, Manel Baradad, Ferran Marques, Jordi Torres, Xavier Giro-i-Nieto

CVPR 2018 DeepVision Workshop

[paper] [www] [code]

Characterizing chronic disease and polymedication prescription patterns from electronic health records

Martí Zamora, Manel Baradad, Ester Amado, Silvia Cordomí, Esther Limón, Juliana Ribera, Marta Arias and Ricard Gavaldà

DSAA 2015

[paper]