3.4k citations · 6.8k across the 36 of their papers we have counts for
40 papers
TAPVid-MV: A Benchmark for Tracking Any Point in 3D Across Multiple Views
Skanda Koppula, Frano Rajic, Abdullah Faiz Ur Rahman +9
Multi-camera systems are increasingly practical for robotics, AR/VR, and autonomous driving because complementary views reduce depth ambiguity and preserve visibility under occlusi…
TAPNext++: What's Next for Tracking Any Point (TAP)?
Sebastian Jung, Artem Zholus, Martin Sundermeyer +6
Tracking-Any-Point (TAP) models aim to track any point through a video which is a crucial task in AR/XR and robotics applications. The recently introduced TAPNext approach proposes…
Forecasting Motion in the Wild
Neerja Thakkar, Shiry Ginosar, Jacob Walker +3
Visual intelligence requires anticipating the future behavior of agents, yet vision systems lack a general representation for motion and behavior. We propose dense point trajectori…
Gemini Robotics 1.5: Pushing the Frontier of Generalist Robots with Advanced Embodied Reasoning, Thinking, and Motion Transfer
Gemini Robotics Team, Abbas Abdolmaleki, Saminda Abeyruwan +169
General-purpose robots need a deep understanding of the physical world, advanced reasoning, and general and dexterous control. This report introduces the latest generation of the G…
Frozen Forecasting: A Unified Evaluation
Jacob C Walker, Pedro Vélez, Luisa Polania Cabrera +7
Forecasting future events is a fundamental capability for general-purpose systems that plan or act across different levels of abstraction. Yet, evaluating whether a forecast is "co…
Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities
Gheorghe Comanici, Eric Bieber, Mike Schaekermann +3431
In this report, we introduce the Gemini 2.X model family: Gemini 2.5 Pro and Gemini 2.5 Flash, as well as our earlier Gemini 2.0 Flash and Flash-Lite models. Gemini 2.5 Pro is our…
Direct Motion Models for Assessing Generated Videos
Kelsey Allen, Carl Doersch, Guangyao Zhou +9
A current limitation of video generative video models is that they generate plausible looking frames, but poor motion -- an issue that is not well captured by FVD and other popular…
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…
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…
Motion Prompting: Controlling Video Generation with Motion Trajectories
Daniel Geng, Charles Herrmann, Junhwa Hur +11
Motion control is crucial for generating expressive and compelling video content; however, most existing video generation models rely mainly on text prompts for control, which stru…
Moving Off-the-Grid: Scene-Grounded Video Representations
Sjoerd van Steenkiste, Daniel Zoran, Yi Yang +13
Current vision models typically maintain a fixed correspondence between their representation structure and image space. Each layer comprises a set of tokens arranged "on-the-grid,"…
Gen2Act: Human Video Generation in Novel Scenarios enables Generalizable Robot Manipulation
Homanga Bharadhwaj, Debidatta Dwibedi, Abhinav Gupta +7
How can robot manipulation policies generalize to novel tasks involving unseen object types and new motions? In this paper, we provide a solution in terms of predicting motion info…
TAPVid-3D: A Benchmark for Tracking Any Point in 3D
Skanda Koppula, Ignacio Rocco, Yi Yang +5
We introduce a new benchmark, TAPVid-3D, for evaluating the task of long-range Tracking Any Point in 3D (TAP-3D). While point tracking in two dimensions (TAP) has many benchmarks m…
BootsTAP: Bootstrapped Training for Tracking-Any-Point
Carl Doersch, Pauline Luc, Yi Yang +8
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. This can be formalized…
Learning from One Continuous Video Stream
João Carreira, Michael King, Viorica Pătrăucean +9
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. This p…
RoboTAP: Tracking Arbitrary Points for Few-Shot Visual Imitation
Mel Vecerik, Carl Doersch, Yi Yang +6
For robots to be useful outside labs and specialized factories we need a way to teach them new useful behaviors quickly. Current approaches lack either the generality to onboard ne…
TAPIR: Tracking Any Point with per-frame Initialization and temporal Refinement
Carl Doersch, Yi Yang, Mel Vecerik +5
We present a novel model for Tracking Any Point (TAP) that effectively tracks any queried point on any physical surface throughout a video sequence. Our approach employs two stages…
Perception Test: A Diagnostic Benchmark for Multimodal Video Models
Viorica Pătrăucean, Lucas Smaira, Ankush Gupta +21
We propose a novel multimodal video benchmark - the Perception Test - to evaluate the perception and reasoning skills of pre-trained multimodal models (e.g. Flamingo, SeViLA, or GP…
TAP-Vid: A Benchmark for Tracking Any Point in a Video
Carl Doersch, Ankush Gupta, Larisa Markeeva +6
Generic motion understanding from video involves not only tracking objects, but also perceiving how their surfaces deform and move. This information is useful to make inferences ab…
Kubric: A scalable dataset generator
Klaus Greff, Francois Belletti, Lucas Beyer +32
Data is the driving force of machine learning, with the amount and quality of training data often being more important for the performance of a system than architecture and trainin…
Input-level Inductive Biases for 3D Reconstruction
Wang Yifan, Carl Doersch, Relja Arandjelović +2
Much of the recent progress in 3D vision has been driven by the development of specialized architectures that incorporate geometrical inductive biases. In this paper we tackle 3D r…
Perceiver IO: A General Architecture for Structured Inputs & Outputs
Andrew Jaegle, Sebastian Borgeaud, Jean-Baptiste Alayrac +12
A central goal of machine learning is the development of systems that can solve many problems in as many data domains as possible. Current architectures, however, cannot be applied…
Inferring a Continuous Distribution of Atom Coordinates from Cryo-EM Images using VAEs
Dan Rosenbaum, Marta Garnelo, Michal Zielinski +10
Cryo-electron microscopy (cryo-EM) has revolutionized experimental protein structure determination. Despite advances in high resolution reconstruction, a majority of cryo-EM experi…
CrossTransformers: spatially-aware few-shot transfer
Carl Doersch, Ankush Gupta, Andrew Zisserman
Given new tasks with very little datasuch as new classes in a classification problem or a domain shift in the inputperformance of modern vision systems degrades remarkably qu…