Gabriel Brostow — accepted AI-conference papers

2026

Cross-View Splatter: Feed-Forward View Synthesis with Georeferenced Images

Matias Turkulainen, Akshay Krishnan, Filippo Aleotti, Mohamed Sayed, Guillermo Garcia-Hernando, Juho Kannala +3

CVPR 2026

We present Cross-View Splatter, a feed-forward method that predicts pixel-aligned Gaussian splats for outdoor scenes captured at ground level and by satellite. Faithful reconstructions require good camera coverage, but ground imagery is time-consuming and hard to capture at scale for large outdoor s

Cited by 0 Source ↗code ↗Scholar ↗

2025

MVSAnywhere: Zero-Shot Multi-View Stereo

Sergio Izquierdo, Mohamed Sayed, Michael Firman, Guillermo Garcia-Hernando, Daniyar Turmukhambetov, Javier Civera +3

CVPR 2025poster

Computing accurate depth from multiple views is a fundamental and longstanding challenge in computer vision.However, most existing approaches do not generalize well across different domains and scene types (e.g. indoor vs outdoor). Training a general-purpose multi-view stereo model is challenging an…

Cited by 3 Source ↗PDF ↗code ↗Scholar ↗

2025

PlaceIt3D: Language-Guided Object Placement in Real 3D Scenes

Ahmed Abdelreheem, Filippo Aleotti, Jamie Watson, Zawar Qureshi, Abdelrahman Eldesokey, Peter Wonka +3

ICCV 2025poster

We introduce the task of Language-Guided Object Placement in Real 3D Scenes. Given a 3D reconstructed point-cloud scene, a 3D asset, and a natural-language instruction, the goal is to place the asset so that the instruction is satisfied. The task demands tackling four intertwined challenges: (a) one…

Cited by 0 Source ↗PDF ↗Scholar ↗

2024

AirPlanes: Accurate Plane Estimation via 3D-Consistent Embeddings

Jamie Watson, Filippo Aleotti, Mohamed Sayed, Zawar Qureshi, Oisin Mac Aodha, Gabriel Brostow +2

CVPR 2024poster

Extracting planes from a 3D scene is useful for downstream tasks in robotics and augmented reality. In this paper we tackle the problem of estimating the planar surfaces in a scene from posed images. Our first finding is that a surprisingly competitive baseline results from combining popular cluster…

Cited by 1 Source ↗PDF ↗Scholar ↗

2024

DoubleTake: Geometry Guided Depth Estimation

Mohamed Sayed*, Filippo Aleotti, Jamie Watson, Zawar Qureshi, Guillermo Garcia-Hernando, Gabriel Brostow +2

ECCV 2024poster

"Estimating depth from a sequence of posed RGB images is a fundamental computer vision task, with applications in augmented reality, path planning etc. Prior work typically makes use of previous frames in a multi view stereo framework, relying on matching textures in a local neighborhood. In contras…

Cited by 1 Source ↗PDF ↗Scholar ↗

2024

GroundUp: Rapid Sketch-Based 3D City Massing

Gizem Esra Unlu*, Mohamed Sayed, Yulia Gryaditskaya, Gabriel Brostow

ECCV 2024poster

"We propose GroundUp, the first sketch-based ideation tool for 3D city massing of urban areas. We focus on early-stage urban design, where sketching is a common tool and the design starts from balancing planned building volumes (masses) and open spaces. With Human-Centered AI in mind, we aim to help…

Cited by 1 Source ↗PDF ↗Scholar ↗

2024

INQUIRE: A Natural World Text-to-Image Retrieval Benchmark

Edward Vendrow, Omiros Pantazis, Alexander Shepard, Gabriel Brostow, Kate E. Jones, Oisin Mac Aodha +2

NeurIPS 2024poster

We introduce INQUIRE, a text-to-image retrieval benchmark designed to challenge multimodal vision-language models on expert-level queries. INQUIRE includes iNaturalist 2024 (iNat24), a new dataset of five million natural world images, along with 250 expert-level retrieval queries. These queries are…

Cited by 1 Source ↗PDF ↗code ↗Scholar ↗

2024

TAPVid-3D: A Benchmark for Tracking Any Point in 3D

Skanda Koppula, Ignacio Rocco, Yi Yang, Joseph Heyward, Joao Carreira, Andrew Zisserman +2

NeurIPS 2024poster

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-2D) has many benchmarks measuring performance on real-world videos, such as TAPVid-DAVIS, three-dimensional point tracking has none. To this e…

Cited by 10 Source ↗PDF ↗code ↗Scholar ↗

2021

Improved Handling of Motion Blur in Online Object Detection

Mohamed Sayed, Gabriel Brostow

CVPR 2021poster

We wish to detect specific categories of objects, for online vision systems that will run in the real world. Object detection is already very challenging. It is even harder when the images are blurred, from the camera being in a car or a hand-held phone. Most existing efforts either focused on sharp…

Cited by 53 PDF ↗Scholar ↗

2021

Panoptic Segmentation Forecasting

Colin Graber, Grace Tsai, Michael Firman, Gabriel Brostow, Alexander G. Schwing

CVPR 2021poster

Our goal is to forecast the near future given a set of recent observations. We think this ability to forecast, i.e., to anticipate, is integral for the success of autonomous agents which need not only passively analyze an observation but also must react to it in real-time. Importantly, accurate fore…

Cited by 19 PDF ↗Scholar ↗

2021

The Temporal Opportunist: Self-Supervised Multi-Frame Monocular Depth

Jamie Watson, Oisin Mac Aodha, Victor Prisacariu, Gabriel Brostow, Michael Firman

CVPR 2021poster

Self-supervised monocular depth estimation networks are trained to predict scene depth using nearby frames as a supervision signal during training. However, for many applications, sequence information in the form of video frames is also available at test time. The vast majority of monocular networks…

Cited by 346 PDF ↗code ↗Scholar ↗

2018

CubeNet: Equivariance to 3D Rotation and Translation

Daniel Worrall, Gabriel Brostow

ECCV 2018poster

3D Convolutional Neural Networks are sensitive to transformations applied to their input. This is a problem because a voxelized version of a 3D object, and its rotated clone, will look unrelated to each other after passing through to the last layer of a network. Instead, an idealized model would pre…

Cited by 176 Source ↗PDF ↗Scholar ↗