Texturepoor SfM Dataset

We collect an SfM dataset composed of 17 object-centric texture-poor scenes with accurate ground-truth poses. In our dataset, low-textured objects are placed on a texture-less plane. For each object, we record a video sequence of around 30 seconds surrounding the object. The ground-truth poses per frame are estimated by ARKit and BA post-processing, with the help of textured markers, which are cropped in the test images. To impose larger viewpoint changes, we sample 60 subset image bags for each scene, similar to the IMC dataset.

本数据集汇聚了17个以物体为中心、纹理贫乏的场景，并附带精确的地面真实姿态。在数据集中，低纹理的物体被放置在无纹理的平面上。对于每个物体，我们记录了一段约30秒的视频序列，环绕该物体周围。每帧的地面真实姿态通过ARKit进行估计，并辅以纹理标记的BA后处理得到，纹理标记在测试图像中被裁剪。为引入更大的视角变化，我们对每个场景采样了60个子图像包，与IMC数据集类似。