8 papers
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,…
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…
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…
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…
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…
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…