Research Scientist Tech Lead & Manager Google DeepMind
Email: contact@msajjadi.com Bluesky: @msajjadi.com Github: msmsajjadi
Mehdi S. M. Sajjadi
Mehdi is a Research Scientist, Tech Lead & Manager at Google DeepMind, where his work focuses on spatio-temporal scene understanding and deep generative models. Recently, he led the project that won the Best Paper Award at CVPR 2026. With over a decade of experience in the field, he is passionate about building systems that can perceive and generate the world in 3D. Previously, he completed his PhD at the Max Planck Institute for Intelligent Systems with Bernhard Schölkopf, supported by a fellowship from ETH Zürich CLS.
Publications (Google Scholar)
- 🔥 Efficiently Reconstructing Dynamic Scenes One 🎯 D4RT at a Time (CVPR 2026 Best Paper 🏆)
-
🔥 From Image to Video: An Empirical Study of Diffusion Representations (ICCV 2025 Highlight, top 2.3%)
-
LayerLock: Non-collapsing Representation Learning with Progressive Freezing (ICCV 2025)
- TAPNext: End-to-End Tracking Any Point as Next Token Prediction (ICCV 2025)
- Scaling 4D Representations
- TRecViT: A Recurrent Video Transformer (TMLR 2026)
- Direct Motion Models for Assessing Generated Videos (ICML 2025)
-
Moving Off-the-Grid: Scene-Grounded Video Representations (NeurIPS 2024 Spotlight, top 2%)
- DyST: Towards Dynamic Neural Scene Representations on Real-World Videos (ICLR 2024 Spotlight, top 5%)
- 🔥 RUST: Latent Neural Scene Representations from Unposed Imagery (CVPR 2023 Highlight, top 2.5%)
- 🔥 PaLM-E: An Embodied Multimodal Language Model (ICML 2023)
- DORSal: Diffusion for Object-centric Representations of Scenes et al. (ICLR 2024)
-
Sensitivity of Slot-Based Object-Centric Models to their Number of Slots
-
RePAST: Relative Pose Attention Scene Representation Transformer (CVPR 2023 Workshops 3DMV & T4V Spotlight)
- Test-time adaptation with slot-centric models (ICML 2023, NeurIPS 2022 Workshops MetaLearn & DistShift)
-
Spatial Symmetry in Slot Attention (ICML 2023, NeurIPS 2022 Workshop NeurReps)
- Object Scene Representation Transformer (NeurIPS 2022)
- 🔥 Scene Representation Transformer: Geometry-Free Novel View Synthesis Through Set-Latent Scene Representations (CVPR 2022)
- RegNeRF: Regularizing Neural Radiance Fields for View Synthesis from Sparse Inputs (CVPR 2022 Oral)
- Kubric (CVPR 2022)
- NeSF: Neural Semantic Fields for Generalizable Semantic Segmentation of 3D Scenes (TMLR 2022)
- NeRF in the Wild (CVPR 2021 Oral)
-
From Variational to Deterministic Autoencoders (ICLR 2020)
- 🔥 Assessing Generative Models via Precision and Recall (NeurIPS 2018 & ICML 2018 workshop TADGM Oral & Best Poster Award at Bosch AI Con 2018)
-
Photorealistic Video Super-Resolution with Enhanced Temporal Consistency (ECCV 2018 workshop PIRM)
-
Spatio-temporal Transformer Network for Video Restoration (ECCV 2018)
-
Tempered Adversarial Networks (ICML 2018 Oral & ICLR 2018 workshop)
- Frame-Recurrent Video Super-Resolution (CVPR 2018)
- 🔥 EnhanceNet: Single Image Super-Resolution Through Automated Texture Synthesis (ICCV 2017 Oral, top 2%)
- Project website
- GitHub
- Our work has been covered in the press:
- Depth Estimation Through a Generative Model of Light Field Synthesis (GCPR 2016)
- Peer Grading in a Course on Algorithms and Data Structures: Machine Learning Algorithms do not Improve over Simple Baselines (L@S 2016 Oral & ICML 2015 workshops CrowdML & ML4Ed)