collaborators

8 papers

cs.CV2026

Why Domain Matters: Domain-Aware Benchmarking of Underwater Object Detection and Annotation Quality

Melanie Wille, Dimity Miller, Tobias Fischer +1

Underwater object detection is strongly affected by domain shift, where performance can vary significantly across different locations, habitats, and deployment conditions. However,…

cs.CV2026

Predictive Photometric Uncertainty in Gaussian Splatting for Novel View Synthesis

Chamuditha Jayanga Galappaththige, Thomas Gottwald, Peter Stehr +4

Recent advances in 3D Gaussian Splatting have enabled impressive photorealistic novel view synthesis. However, to transition from a pure rendering engine to a reliable spatial map…

cs.CV2026

From Pixels to Primitives: Scene Change Detection in 3D Gaussian Splatting

Chamuditha Jayanga Galappaththige, Jason Lai, Timothy Patten +3

Scene change detection methods built on Gaussian splatting universally follow a render-then-compare paradigm: the pre-change scene is rendered into 2D and compared against post-cha…

cs.CV2026

Why Domain Matters: A Preliminary Study of Domain Effects in Underwater Object Detection

Melanie Wille, Dimity Miller, Tobias Fischer +1

Domain shift, where deviations between training and deployment data distributions degrade model performance, is a key challenge in underwater environments. Existing benchmarks test…

cs.CV2026

Changes in Real Time: Online Scene Change Detection with Multi-View Fusion

Chamuditha Jayanga Galappaththige, Jason Lai, Lloyd Windrim +3

Online Scene Change Detection (SCD) is an extremely challenging problem that requires an agent to detect relevant changes on the fly while observing the scene from unconstrained vi…

cs.CV2025

Intra-Class Probabilistic Embeddings for Uncertainty Estimation in Vision-Language Models

Zhenxiang Lin, Maryam Haghighat, Will Browne +1

Vision-language models (VLMs), such as CLIP, have gained popularity for their strong open vocabulary classification performance, but they are prone to assigning high confidence sco…