183 citations · 310 across the 24 of their papers we have counts for
28 papers · 1 filter
INQUIRE: A Natural World Text-to-Image Retrieval Benchmark
Edward Vendrow, Omiros Pantazis, Alexander Shepard +5
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…
Deep learning-based ecological analysis of camera trap images is impacted by training data quality and quantity
Peggy A. Bevan, Omiros Pantazis, Holly Pringle +10
Large image collections generated from camera traps offer valuable insights into species richness, occupancy, and activity patterns, significantly aiding biodiversity monitoring. H…
Two-View Geometry Scoring Without Correspondences
Axel Barroso-Laguna, Eric Brachmann, Victor Adrian Prisacariu +2
Camera pose estimation for two-view geometry traditionally relies on RANSAC. Normally, a multitude of image correspondences leads to a pool of proposed hypotheses, which are then s…
Virtual Occlusions Through Implicit Depth
Jamie Watson, Mohamed Sayed, Zawar Qureshi +4
For augmented reality (AR), it is important that virtual assets appear to `sit among' real world objects. The virtual element should variously occlude and be occluded by real matte…
Removing Objects From Neural Radiance Fields
Silvan Weder, Guillermo Garcia-Hernando, Aron Monszpart +4
Neural Radiance Fields (NeRFs) are emerging as a ubiquitous scene representation that allows for novel view synthesis. Increasingly, NeRFs will be shareable with other people. Befo…
Interactive Sketching of Mannequin Poses
Gizem Unlu, Mohamed Sayed, Gabriel Brostow
It can be easy and even fun to sketch humans in different poses. In contrast, creating those same poses on a 3D graphics "mannequin" is comparatively tedious. Yet 3D body poses are…
SVL-Adapter: Self-Supervised Adapter for Vision-Language Pretrained Models
Omiros Pantazis, Gabriel Brostow, Kate Jones +1
Vision-language models such as CLIP are pretrained on large volumes of internet sourced image and text pairs, and have been shown to sometimes exhibit impressive zero- and low-shot…
Focus on the Positives: Self-Supervised Learning for Biodiversity Monitoring
Omiros Pantazis, Gabriel Brostow, Kate Jones +1
We address the problem of learning self-supervised representations from unlabeled image collections. Unlike existing approaches that attempt to learn useful features by maximizing…
Visual Camera Re-Localization Using Graph Neural Networks and Relative Pose Supervision
Mehmet Ozgur Turkoglu, Eric Brachmann, Konrad Schindler +2
Visual re-localization means using a single image as input to estimate the camera's location and orientation relative to a pre-recorded environment. The highest-scoring methods are…
Panoptic Segmentation Forecasting
Colin Graber, Grace Tsai, Michael Firman +2
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…
The Temporal Opportunist: Self-Supervised Multi-Frame Monocular Depth
Jamie Watson, Oisin Mac Aodha, Victor Prisacariu +2
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,…
Improved Handling of Motion Blur in Online Object Detection
Mohamed Sayed, Gabriel Brostow
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 th…
DiverseNet: When One Right Answer is not Enough
Michael Firman, Neill D. F. Campbell, Lourdes Agapito +1
Many structured prediction tasks in machine vision have a collection of acceptable answers, instead of one definitive ground truth answer. Segmentation of images, for example, is s…
Single-Image Depth Prediction Makes Feature Matching Easier
Carl Toft, Daniyar Turmukhambetov, Torsten Sattler +2
Good local features improve the robustness of many 3D re-localization and multi-view reconstruction pipelines. The problem is that viewing angle and distance severely impact the re…
Learning Stereo from Single Images
Jamie Watson, Oisin Mac Aodha, Daniyar Turmukhambetov +2
Supervised deep networks are among the best methods for finding correspondences in stereo image pairs. Like all supervised approaches, these networks require ground truth data duri…
Image Stylization for Robust Features
Iaroslav Melekhov, Gabriel J. Brostow, Juho Kannala +1
Local features that are robust to both viewpoint and appearance changes are crucial for many computer vision tasks. In this work we investigate if photorealistic image stylization…
Predicting Visual Overlap of Images Through Interpretable Non-Metric Box Embeddings
Anita Rau, Guillermo Garcia-Hernando, Danail Stoyanov +2
To what extent are two images picturing the same 3D surfaces? Even when this is a known scene, the answer typically requires an expensive search across scale space, with matching a…
Footprints and Free Space from a Single Color Image
Jamie Watson, Michael Firman, Aron Monszpart +1
Understanding the shape of a scene from a single color image is a formidable computer vision task. However, most methods aim to predict the geometry of surfaces that are visible to…
Self-Supervised Monocular Depth Hints
Jamie Watson, Michael Firman, Gabriel J. Brostow +1
Monocular depth estimators can be trained with various forms of self-supervision from binocular-stereo data to circumvent the need for high-quality laser scans or other ground-trut…
Digging Into Self-Supervised Monocular Depth Estimation
Clément Godard, Oisin Mac Aodha, Michael Firman +1
Per-pixel ground-truth depth data is challenging to acquire at scale. To overcome this limitation, self-supervised learning has emerged as a promising alternative for training mode…
CubeNet: Equivariance to 3D Rotation and Translation
Daniel Worrall, Gabriel Brostow
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…
Interpretable Transformations with Encoder-Decoder Networks
Daniel E. Worrall, Stephan J. Garbin, Daniyar Turmukhambetov +1
Deep feature spaces have the capacity to encode complex transformations of their input data. However, understanding the relative feature-space relationship between two transformed…
Harmonic Networks: Deep Translation and Rotation Equivariance
Daniel E. Worrall, Stephan J. Garbin, Daniyar Turmukhambetov +1
Translating or rotating an input image should not affect the results of many computer vision tasks. Convolutional neural networks (CNNs) are already translation equivariant: input…
Swipe Mosaics from Video
Malcolm Reynolds, Tom S. F. Haines, Gabriel J. Brostow
A panoramic image mosaic is an attractive visualization for viewing many overlapping photos, but its images must be both captured and processed correctly to produce an acceptable c…