0
0

Delete article

Deleted articles cannot be recovered.

Draft of this article would be also deleted.

Are you sure you want to delete this article?

TransCG 透明物体の把持のためのデータセットの例

Last updated at Posted at 2024-07-29

これも、透明物体の把持のためのデータセット

pdf TransCG: A Large-Scale Real-World Dataset for Transparent Object Depth Completion and A
Grasping Baseline

github https://github.com/Galaxies99/TransCG
transcg dataset https://graspnet.net/transcg

TransCG: TransCG is the first large-scale real-world dataset for transparent object depth completion and grasping. We provide the original RGB-D images as well as the refined ground-truth depth images in the dataset. The transparent object pose, transparent object mask, the ground-truth surface normals and transparent object models are also provided.

Intel RealSense D435 camera and an Intel RealSense L515 camera.

Screenshot from 2024-07-29 11-59-27.png

Screenshot from 2024-07-29 12-01-24.png

Screenshot from 2024-07-29 12-01-35.png

Screenshot from 2024-07-29 12-01-53.png

Screenshot from 2024-07-29 12-02-07.png

Screenshot from 2024-07-29 12-11-21.png

Fig. 3 の中で、3D scannerを別途使用している。

we temporarily wrap the transparent object with some opaque materials that can preserve the shape of objects, and obtain its 3D model with a Shining3D EinScan-SP scanner2.
透明な物体を、物体の形状を保持できる不透明な材料で仮包し、Shining3D EinScan-SPスキャナ2 を使って3Dモデルを取得する。

問題を扱いやすくするために、fixer with markerを使っている。
それを使うことで、姿勢の算出がしやすくなっっている。

3D scanner

    |   |-- rgb1.png                    # RGB image of perspective 0 (D435 camera) (if exists)
    |   |-- depth1.png                  # Raw depth image of perspective 0 (D435 camera) (if exists)       
    |   |-- depth1-gt.png               # Refined ground-truth depth image of perspective 0 (D435 camera) (if exists)  
    |   |-- depth1-gt-mask.png          # Transparent object mask for depth image of perspective 0 (D435 camera) (if exists)
    |   |-- depth1-gt-sn.png            # Ground-truth surface normals of perspective 0 (D435 camera) (if exists)

データセットのファイル構成については https://graspnet.net/transcg に記載がある。

DFNet

  • この論文中で提案しているdepth算出のアルゴリズム
    Screenshot from 2024-07-29 12-23-25.png

ClearGrasp, LIF-Rfine, TranspareNet, DFNet との比較を実施している。

DFNet では、model size が小さく Inference Timeも少ない。(Table II)

Error Mapの値が小さいものがよい。(Fig. 5)

DFNetのアルゴリズムの中では、RGB画像と不十分なdepthデータをもとに、refined Depthを算出している。
(Fig. 4)

0
0
0

Register as a new user and use Qiita more conveniently

  1. You get articles that match your needs
  2. You can efficiently read back useful information
  3. You can use dark theme
What you can do with signing up
0
0

Delete article

Deleted articles cannot be recovered.

Draft of this article would be also deleted.

Are you sure you want to delete this article?