Research
Training-Free Temporal Abstraction for General Video Understanding
Etienne Casanova, Sevan Brodjian, Pietro Perona
Preprint · May 2026
In this paper we demonstrate that pretrained foundation models provide a general video understanding backbone across moment retrieval, generic event boundary detection, and long-video frame selection for VLMs.
Single-View Seafloor Recovery from Imaging Sonar via Differentiable Rendering
Sevan Brodjian, Michael Hobley, Pietro Perona
Accepted (Poster) · CVPR PBVS Workshop · March 2026
Forward-looking sonar collapses the entire vertical structure of a 3D scene into a single flat, ambiguous image, which made inverting it an interesting problem. We built a fully differentiable renderer of the acoustic acquisition physics and let gradient descent do the rest, recovering seafloor and riverbed geometry from a single frame with no training data.
Kuramoto Orientation Diffusion Models
Yue Song, T. Anderson Keller, Sevan Brodjian et al.
Accepted (Poster) · NeurIPS 2025 · September 2025
Biological neural systems synchronize through Kuramoto oscillator dynamics. We built off that mechanism to create a diffusion model out of it, using phase synchronization as a structured prior for generating orientation-rich images like fingerprints and textures.