← Back to all news
arXiv Computer Vision By Risto Ojala, Tristan Ellison, Mo Chen

Glass Segmentation with Fusion of Learned and General Visual Features

Read the original on arXiv Computer Vision →

The paper introduces a dual‑backbone architecture for glass segmentation that combines a frozen foundation model with a learned backbone trained on glass‑specific data. By fusing hierarchical multi‑scale features from both backbones, the method produces accurate segmentation masks and achieves state‑of‑the‑art performance on four benchmark datasets. Ablation studies confirm the benefits of the dual‑backbone design and its generalizability across different backbone choices, while also offering competitive inference speeds, especially with lighter backbones.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computer Vision.

Related stories

arXiv Computer Vision
Aug 28

Glass Surface Detection Grounded in 3D Visual Geometry

Glass Surface Detection Grounded in 3D Visual Geometry proposes a new approach that grounds glass surface detection in 3D visual geometry rather than relying solely on 2D appearance cues. The method uses a visual geometry grounded transformer (VGGT) to distill 3D priors and creates glass-aware 3D representations, then applies a multi-task learning framework with a Frequency Self-Attention Module (FSAM) and a Geometry Grounding Block (GeGB) to localize and segment glass surfaces. Experiments show state‑of‑the‑art performance on seven benchmarks, good generalization to video and multi‑modal data, and significant improvements in reconstruction of glass scenes.

By Yiwei Lu, Ke Xu, Tao Yan, Xiaojun Chang, Radu Timofte, Rynson W. H. Lau
llmscomputer-visionmultimodalbenchmarks
More like this →
arXiv Computer Vision
Sep 25

PePESeg3D: Perception Prior Enhances Multi-Scale Segmentation for 3D Gaussian Splatting

PePESeg3D introduces perception priors into a multi‑scale 3D Gaussian segmentation pipeline, integrating monocular depth and mask constraints during geometry reconstruction and dense depth‑color cues with view‑consistent centroid supervision during contrastive feature learning. This dual‑stage approach aligns geometry with semantic structure and compensates for incomplete mask supervision from 2D foundation models. Experiments on SPIn‑NeRF, LERF‑Mask, and NVOS benchmarks show state‑of‑the‑art performance in both multi‑scale segmentation and scene reconstruction.

By Sungjae Choi, Seunghee Koh, Junmo Kim
computer-visionbenchmarks
More like this →