Self-Supervised Learning for Transparent Object Depth Completion Using Depth from Non-Transparent Objects
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866918231960190976 |
|---|---|
| author | Fan, Xianghui Chen, Zhaoyu Pan, Mengyang Deng, Anping Yang, Hang |
| author_facet | Fan, Xianghui Chen, Zhaoyu Pan, Mengyang Deng, Anping Yang, Hang |
| contents | The perception of transparent objects is one of the well-known challenges in computer vision. Conventional depth sensors have difficulty in sensing the depth of transparent objects due to refraction and reflection of light. Previous research has typically train a neural network to complete the depth acquired by the sensor, and this method can quickly and accurately acquire accurate depth maps of transparent objects. However, previous training relies on a large amount of annotation data for supervision, and the labeling of depth maps is costly. To tackle this challenge, we propose a new self-supervised method for training depth completion networks. Our method simulates the depth deficits of transparent objects within non-transparent regions and utilizes the original depth map as ground truth for supervision. Experiments demonstrate that our method achieves performance comparable to supervised approach, and pre-training with our method can improve the model performance when the training samples are small. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2512_05006 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Self-Supervised Learning for Transparent Object Depth Completion Using Depth from Non-Transparent Objects Fan, Xianghui Chen, Zhaoyu Pan, Mengyang Deng, Anping Yang, Hang Computer Vision and Pattern Recognition The perception of transparent objects is one of the well-known challenges in computer vision. Conventional depth sensors have difficulty in sensing the depth of transparent objects due to refraction and reflection of light. Previous research has typically train a neural network to complete the depth acquired by the sensor, and this method can quickly and accurately acquire accurate depth maps of transparent objects. However, previous training relies on a large amount of annotation data for supervision, and the labeling of depth maps is costly. To tackle this challenge, we propose a new self-supervised method for training depth completion networks. Our method simulates the depth deficits of transparent objects within non-transparent regions and utilizes the original depth map as ground truth for supervision. Experiments demonstrate that our method achieves performance comparable to supervised approach, and pre-training with our method can improve the model performance when the training samples are small. |
| title | Self-Supervised Learning for Transparent Object Depth Completion Using Depth from Non-Transparent Objects |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2512.05006 |