activity
20242026
collaborators

6 papers

cs.CV2026

A Mixed Diet Makes DINO An Omnivorous Vision Encoder

Rishabh Kabra, Maks Ovsjanikov, Drew A. Hudson +5

Pre-trained vision encoders like DINOv2 have demonstrated exceptional performance on unimodal tasks. However, we observe that their features are poorly aligned across different vis…

cs.CV2025

Efficiently Reconstructing Dynamic Scenes One D4RT at a Time

Chuhan Zhang, Guillaume Le Moing, Skanda Koppula +11

Understanding and reconstructing the complex geometry and motion of dynamic scenes from video remains a formidable challenge in computer vision. This paper introduces D4RT, a simpl…

cs.CV2025

Scaling 4D Representations

João Carreira, Dilara Gokay, Michael King +32

Scaling has not yet been convincingly demonstrated for pure self-supervised learning from video. However, prior work has focused evaluations on semantic-related tasks $\unicode{x20…

cs.CV2025

SciVid: Cross-Domain Evaluation of Video Models in Scientific Applications

Yana Hasson, Pauline Luc, Liliane Momeni +10

In recent years, there has been a proliferation of spatiotemporal foundation models in different scientific disciplines. While promising, these models are often domain-specific and…

cs.CV2025

TAPNext: Tracking Any Point (TAP) as Next Token Prediction

Artem Zholus, Carl Doersch, Yi Yang +7

Tracking Any Point (TAP) in a video is a challenging computer vision problem with many demonstrated applications in robotics, video editing, and 3D reconstruction. Existing methods…

cs.CV2024

A Simple Recipe for Contrastively Pre-training Video-First Encoders Beyond 16 Frames

Pinelopi Papalampidi, Skanda Koppula, Shreya Pathak +7

Understanding long, real-world videos requires modeling of long-range visual dependencies. To this end, we explore video-first architectures, building on the common paradigm of tra…