Extended Unimelb Corridor
收藏资源简介：
We used a subset of synthetic images that only contained forward-looking images from the original Unimelb corridor dataset, and removed the additional images that were generated by rotating the camera along the X and Y axes. To compensate for the low number of synthetic images, we generated 900 more images along the original trajectory by reducing the spacing between the consecutive images, which finally resulted in 1400 images for the synthetic dataset. The dataset also contains 950 real images and their corresponding groundtruth camera poses in the BIM coordinate system. We removed some of the redundant images (100) at the end of the trajectory and added another 500 new real images, which resulted in 1350 real images. The synthetic and real cameras have identical intrinsic camera parameters, with an image resolution of 640 x 480 pixels. Additionally, the provided Blender files can be used to render the images. Please note that SynCar dataset should be rendered with Blender 2.78 only, whereas SynPhoReal and SynPhoRealTex images can be generated using the latest Blender 3.4. [1] Acharya, D., Khoshelham, K. and Winter, S., 2019. BIM-PoseNet: Indoor camera localisation using a 3D indoor model and deep learning from synthetic images. ISPRS Journal of Photogrammetry and Remote Sensing, 150, pp.245-258. [2] Acharya, D., Singha Roy, S., Khoshelham, K. and Winter, S., 2020. A recurrent deep network for estimating the pose of real indoor images from synthetic image sequences. Sensors, 20(19), p.5492. [3] Acharya, D., Tennakoon, R., Muthu, S., Khoshelham, K., Hoseinnezhad, R. and Bab-Hadiashar, A., 2022. Single-image localisation using 3D models: Combining hierarchical edge maps and semantic segmentation for domain adaptation. Automation in Construction, 136, p.104152.
我们从原始Unimelb走廊数据集中选取仅包含前视视角的合成图像子集，并移除了通过沿X、Y轴旋转相机生成的额外图像。为弥补合成图像数量匮乏的问题，我们通过缩小连续图像间的采样间距，沿原始轨迹额外生成了900张图像，最终合成数据集总计包含1400张图像。 该数据集同时包含950张真实图像，以及这些图像在建筑信息模型（BIM）坐标系下对应的相机位姿真值。我们移除了轨迹末端的100张冗余真实图像，并新增了500张全新的真实图像，最终真实图像总数达到1350张。 合成相机与真实相机的内参完全一致，图像分辨率均为640×480像素。此外，本次提供的Blender文件可用于该数据集图像的渲染。 请注意，SynCar数据集仅可使用Blender 2.78版本进行渲染，而SynPhoReal与SynPhoRealTex图像可通过最新的Blender 3.4版本生成。 [1] Acharya, D., Khoshelham, K. 及 Winter, S., 2019. BIM-PoseNet：基于三维室内模型与合成图像深度学习的室内相机定位. ISPRS摄影测量与遥感学报, 150, 第245-258页. [2] Acharya, D., Singha Roy, S., Khoshelham, K. 及 Winter, S., 2020. 用于从合成图像序列估计真实室内图像位姿的循环深度网络. 传感器, 20(19), 第5492页. [3] Acharya, D., Tennakoon, R., Muthu, S., Khoshelham, K., Hoseinnezhad, R. 及 Bab-Hadiashar, A., 2022. 基于三维模型的单图像定位：结合层级边缘图与语义分割实现域自适应. 自动化建造, 136, 第104152页.
