13 papers
TIDES: Time-Derivative Event Simulation via Deformable Reconstruction
Christopher Thirgood, Dipon Kumar Ghosh, Simon Hadfield
Event cameras emit asynchronous events in response to environmental appearance changes. The scarcity of real-world event datasets makes simulation essential. However, most simulato…
TACO: Trajectory Aligning Cross-view Optimisation
Tavis Shore, Oscar Mendez, Simon Hadfield
Cross-View Geo-localisation (CVGL) matches ground imagery against satellite tiles to give absolute position fixes, an alternative to GNSS where signals are occluded, jammed, or spo…
FeatureSLAM: Feature-enriched 3D gaussian splatting SLAM in real time
Christopher Thirgood, Oscar Mendez, Erin Ling +2
We present a real-time tracking SLAM system that unifies efficient camera tracking with photorealistic feature-enriched mapping using 3D Gaussian Splatting (3DGS). Our main contrib…
HYDRA: HYbrid knowledge Distillation and spectral Reconstruction Algorithm for high channel hyperspectral camera applications
Christopher Thirgood, Oscar Mendez, Erin Ling +2
Hyperspectral images (HSI) promise to support a range of new applications in computer vision. Recent research has explored the feasibility of generalizable Spectral Reconstruction…
VICI: VLM-Instructed Cross-view Image-localisation
Xiaohan Zhang, Tavis Shore, Chen Chen +3
In this paper, we present a high-performing solution to the UAVM 2025 Challenge, which focuses on matching narrow FOV street-level images to corresponding satellite imagery using t…
HyperGS: Hyperspectral 3D Gaussian Splatting
Christopher Thirgood, Oscar Mendez, Erin Chao Ling +2
We introduce HyperGS, a novel framework for Hyperspectral Novel View Synthesis (HNVS), based on a new latent 3D Gaussian Splatting (3DGS) technique. Our approach enables simultaneo…
PEnG: Pose-Enhanced Geo-Localisation
Tavis Shore, Oscar Mendez, Simon Hadfield
Cross-view Geo-localisation is typically performed at a coarse granularity, because densely sampled satellite image patches overlap heavily. This heavy overlap would make disambigu…
SpaGBOL: Spatial-Graph-Based Orientated Localisation
Tavis Shore, Oscar Mendez, Simon Hadfield
Cross-View Geo-Localisation within urban regions is challenging in part due to the lack of geo-spatial structuring within current datasets and techniques. We propose utilising grap…
RenDetNet: Weakly-supervised Shadow Detection with Shadow Caster Verification
Nikolina Kubiak, Elliot Wortman, Armin Mustafa +3
Existing shadow detection models struggle to differentiate dark image areas from shadows. In this paper, we tackle this issue by verifying that all detected shadows are real, i.e.…
Single-image coherent reconstruction of objects and humans
Sarthak Batra, Partha P. Chakrabarti, Simon Hadfield +1
Existing methods for reconstructing objects and humans from a monocular image suffer from severe mesh collisions and performance limitations for interacting occluding objects. This…
S3R-Net: A Single-Stage Approach to Self-Supervised Shadow Removal
Nikolina Kubiak, Armin Mustafa, Graeme Phillipson +2
In this paper we present S3R-Net, the Self-Supervised Shadow Removal Network. The two-branch WGAN model achieves self-supervision relying on the unify-and-adaptphenomenon - it unif…
BEV-CV: Birds-Eye-View Transform for Cross-View Geo-Localisation
Tavis Shore, Simon Hadfield, Oscar Mendez
Cross-view image matching for geo-localisation is a challenging problem due to the significant visual difference between aerial and ground-level viewpoints. The method provides loc…
ZeST-NeRF: Using temporal aggregation for Zero-Shot Temporal NeRFs
Violeta Menéndez González, Andrew Gilbert, Graeme Phillipson +2
In the field of media production, video editing techniques play a pivotal role. Recent approaches have had great success at performing novel view image synthesis of static scenes.…