SceneNN：带有注释的场景网格数据集,RGB-D 场景数据集

我们引入了一个由 100 多个室内场景组成的 RGB-D 场景数据集。我们的场景是在马萨诸塞大学波士顿分校和新加坡科技设计大学的办公室、宿舍、教室、食品储藏室等各个地方拍摄的。所有场景都被重建为三角形网格，并具有每个顶点和每个像素的注释。我们使用细粒度信息进一步丰富了数据集，例如轴对齐边界框、定向边界框和对象姿势。 SceneNN: A Scene Meshes Dataset with aNNotations Binh-Son Hua, Quang-Hieu Pham, Duc Thanh Nguyen, Minh-Khoi Tran, Lap-Fai Yu, and Sai-Kit Yeung International Conference on 3D Vision (3DV) 2016. Best Paper Honorable Mention.

We introduce an RGB-D scene dataset consisting of over 100 indoor scenes. The scenes were captured in various locations including offices, dormitories, classrooms, and pantries at the University of Massachusetts Boston and the Singapore University of Technology and Design. All scenes have been reconstructed into triangular meshes, with per-vertex and per-pixel annotations. We further enrich the dataset with fine-grained information such as axis-aligned bounding boxes, oriented bounding boxes, and object poses.
SceneNN: A Scene Meshes Dataset with aNNotations
Binh-Son Hua, Quang-Hieu Pham, Duc Thanh Nguyen, Minh-Khoi Tran, Lap-Fai Yu, and Sai-Kit Yeung
International Conference on 3D Vision (3DV) 2016. Best Paper Honorable Mention.

搜集汇总

背景与挑战

背景概述

SceneNN是一个包含100多个室内场景的RGB-D数据集，涵盖多种场景类型如办公室、宿舍等，并提供丰富的注释信息如网格、顶点注释和对象姿势。该数据集在2016年国际3D视觉会议上获得最佳论文荣誉提名。