{"ID":2833108,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2512.05006","arxiv_id":"2512.05006","title":"Self-Supervised Learning for Transparent Object Depth Completion Using Depth from Non-Transparent Objects","abstract":"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.","short_abstract":"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 sen...","url_abs":"https://arxiv.org/abs/2512.05006","url_pdf":"https://arxiv.org/pdf/2512.05006v1","authors":"[\"Xianghui Fan\",\"Zhaoyu Chen\",\"Mengyang Pan\",\"Anping Deng\",\"Hang Yang\"]","published":"2025-12-04T17:17:47Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[]","has_code":false}