The Flow has not summarised this story yet — read it at arXiv Computer Vision.
The paper introduces AquaOV255, a large-scale underwater segmentation dataset with 255 categories and over 20,000 images, and establishes the UOVSBench benchmark by combining it with five other datasets. It also presents Earth2Ocean, a training‑free open‑vocabulary segmentation framework that adapts terrestrial vision‑language models to underwater scenes using a Geometric‑guided Visual Mask Generator and a Category‑visual Semantic Alignment module. Experiments on UOVSBench show that Earth2Ocean significantly improves performance while keeping inference efficient.
Open-vocabulary remote sensing segmentation has recently emerged as a promising paradigm that enables pixel-level recognition of arbitrary categories specified by natural language, including classes unseen during training. However, geospatial domain shifts caused by heterogeneous regions, spatial resolutions, and acquisition platforms weaken visual-text matching and limit cross-dataset generalization.
CoralscapesV2 is an expanded dataset for coral reef visual scene understanding, increasing the number of fine‑grained classes from 39 to 95 and adding 65,000 exhaustive fish instance masks. It supports panoptic segmentation by providing high‑quality semantic and instance labels across diverse, unconstrained reef imagery. The dataset serves as a challenging benchmark for modern segmentation models and enables broader applications such as benthic cover mapping and automated fish‑reef interaction analysis.
arXiv:2508.11256v2 Announce Type: replace-cross Abstract: Dense visual perception tasks have been constrained by their reliance on predefined categories, limiting their applicability in real-world sc...
arXiv:2610.33478v1 Announce Type: cross Abstract: Marine video understanding is crucial for a wide range of real-world applications. However, existing marine video datasets suffer from limitations, i...
arXiv:2610.35312v1 Announce Type: new Abstract: Monocular occupancy prediction in indoor scenes aims to recover a scene's 3D geometry and semantics from a single RGB image. Existing methods are restr...