Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
SC-Depth (V1, V2, and V3) for Unsupervised Monocular Depth Estimation Webpage:https://jiawangbian.github.io/sc_depth_pl/
| Date | Stars |
|---|---|
| 2026-07-24 | 487 |
| 2026-07-25 | 487 |
| 2026-07-28 | 487 |
| 2026-07-30 | 487 |
| 2026-08-06 | 487 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.00%/day
# SC_Depth: This repo provides the pytorch lightning implementation of **SC-Depth** (V1, V2, and V3) for **self-supervised learning of monocular depth from video**. In the SC-DepthV1 ([IJCV 2021](https://jwbian.net/Papers/SC_Depth_IJCV_21.pdf) & [NeurIPS 2019](https://papers.nips.cc/paper/2019/file/6364d3f0f495b6ab9dcf8d3b5c6e0b01-Paper.pdf)), we propose (i) **geometry consistency loss** for scale-consistent depth prediction over time and (ii) **self-discovered mask** for detecting and removing dynamic regions and occlusions during training towards higher accuracy. The predicted depth is sufficiently accurate and consistent for use in the ORB-SLAM2 system. The below video showcases the estimated depth in the form of pointcloud (top) and color map (bottom right). [<img src="https://jwbian.net/wp-content/uploads/2020/06/[email protected]" width="600">](https://www.youtube.com/watch?v=OkfK3wmMnpo) In the SC-DepthV2 ([TPMAI 2022](https://arxiv.org/abs/2006.02708v2)), we prove that the large relative rotational motions in the hand-held camera captured videos is the main challenge for unsupervised monocular depth estimation in indoor scenes. Based on this findings, we propose auto-recitify network (**ARN**) to handle the large relative rotation between consecutive video frames. It is integrated into SC-DepthV1 and jointly trained with self-supervised losses, greatly boosting the performance. <img src="https://jwbian.net/wp-content/uploads/2020/06/vis_depth.png" width="600"> In the SC-DepthV3 ([TPAMI 2023](https://arxiv.org/abs/2211.03660)), we propose a robust learning framework for accurate and sharp monocular depth estimation in (highly) dynamic scenes. As the photometric loss, which is the main loss in the self-supervised methods, is not valid in dynamic object regions and occlusion, previous methods show poor accuracy in dynamic scenes and blurred depth prediction at object boundaries. We propose to leverage an external pretrained depth estimation network for generating the single-image depth prior, based on which we propose effective losses to constrain self-supervised depth learning. The evaluation results on six challenging datasets including both static and dynamic scenes demonstrate the efficacy of the proposed method. Qualitative depth estimation results: DDAD, BONN, TUM, IBIMS-1 <img src="https://jwbian.net/Demo/vis_ddad.jpg" width="400"> <img src="https://jwbian.net/Demo/vis_bonn.jpg" width="400"> <img src="https://jwbian.net/Demo/vis_tum.jpg" width="400"> <img src="https://jwbian.net/Demo/vis_ibims.jpg" width="400"> Demo Videos https://user-images.githubusercontent.com/11647217/201716221-94fb20ec-0947-4ea0-b83e-572ffa9a46b5.mp4 <img align="left" src="https://user-images.githubusercontent.com/11647217/201711956-7d2c2f48-8d3c-4c05-9402-9e4115e4b5d7.mp4" width="400"> <img align="left" src="https://user-images.githubusercontent.com/11647217/201712014-decd56ba-16eb-4772-90fb-200d489c309c.mp4" width="400"> ## Install ``` conda create -n sc_depth_env python=3.8 conda activate sc_depth_env conda install pytorch torchvision pytorch-cuda=11.7 -c pytorch -c nvidia pip install -r requirements.txt ``` ## Dataset We organize the video datasets into the following format for training and testing models: Dataset -Training --Scene0000 ---*.jpg (list of color images) ---cam.txt (3x3 camera intrinsic matrix) ---depth (a folder containing ground-truth depth maps, optional for validation) ---leres_depth (a folder containing psuedo-depth generated by LeReS, it is required for training SC-DepthV3) --Scene0001 ... train.txt (containing training scene names) val.txt (containing validation scene names) -Testing --color (containg testing images) --depth (containg ground-truth depths) --seg_mask (containing semantic segmentation masks for depth evaluation on dynamic/static regions) We provide pre
Excerpt of 10,950 characters
Read on GitHubWould you bet a product on this? Bounded 0–100 and slow moving.
matched fp:35fc17192c63cf79, topic:computer-vision, topic:pose-estimation, readme:semantic segmentation