BootsTAP: Bootstrapped Training for Tracking-Any-Point

2 code implementations • 1 Feb 2024 • Carl Doersch, Yi Yang, Dilara Gokay, Pauline Luc, Skanda Koppula, Ankush Gupta, Joseph Heyward, Ross Goroshin, João Carreira, Andrew Zisserman

To endow models with greater understanding of physics and motion, it is useful to enable them to perceive how solid surfaces move and deform in real scenes.

Learning from One Continuous Video Stream

no code implementations • 1 Dec 2023 • João Carreira, Michael King, Viorica Pătrăucean, Dilara Gokay, Cătălin Ionescu, Yi Yang, Daniel Zoran, Joseph Heyward, Carl Doersch, Yusuf Aytar, Dima Damen, Andrew Zisserman

We introduce a framework for online learning from a single continuous video stream -- the way people and animals learn, without mini-batches, data augmentation or shuffling.

Data Augmentation Future prediction

TAPIR: Tracking Any Point with per-frame Initialization and temporal Refinement

1 code implementation • ICCV 2023 • Carl Doersch, Yi Yang, Mel Vecerik, Dilara Gokay, Ankush Gupta, Yusuf Aytar, Joao Carreira, Andrew Zisserman

We present a novel model for Tracking Any Point (TAP) that effectively tracks any queried point on any physical surface throughout a video sequence.

Motion Estimation Visual Tracking

Graph2Pix: A Graph-Based Image to Image Translation Framework

1 code implementation • 22 Aug 2021 • Dilara Gokay, Enis Simsar, Efehan Atici, Alper Ahmetoglu, Atif Emre Yuksel, Pinar Yanardag

In this paper, we propose a graph-based image-to-image translation framework for generating images.

Image-to-Image Translation Translation