diff --git a/README.md b/README.md index 8358749..8dbda0b 100644 --- a/README.md +++ b/README.md @@ -21,7 +21,7 @@ This work presents Depth Anything, a highly practical solution for robust monocu * **2024-02-05:** [Depth Anything Gallery](./gallery.md) is released. Thank all the users! * **2024-02-02:** Depth Anything serves as the default depth processor for [InstantID](https://github.com/InstantID/InstantID) and [InvokeAI](https://github.com/invoke-ai/InvokeAI/releases/tag/v3.6.1). -* **2024-01-25:** Support [video depth visualization](./run_video.py). +* **2024-01-25:** Support [video depth visualization](./run_video.py). An [online demo for video](https://huggingface.co/spaces/JohanDL/Depth-Anything-Video) is also available. * **2024-01-23:** The new ControlNet based on Depth Anything is integrated into [ControlNet WebUI](https://github.com/Mikubill/sd-webui-controlnet) and [ComfyUI's ControlNet](https://github.com/Fannovel16/comfyui_controlnet_aux). * **2024-01-23:** Depth Anything [ONNX](https://github.com/fabio-sim/Depth-Anything-ONNX) and [TensorRT](https://github.com/spacewalk01/depth-anything-tensorrt) versions are supported. * **2024-01-22:** Paper, project page, code, models, and demo ([HuggingFace](https://huggingface.co/spaces/LiheYoung/Depth-Anything), [OpenXLab](https://openxlab.org.cn/apps/detail/yyfan/depth_anything)) are released. @@ -29,6 +29,8 @@ This work presents Depth Anything, a highly practical solution for robust monocu ## Features of Depth Anything +***If you need other features, please first check [existing community supports](#community-support).*** + - **Relative depth estimation**: Our foundation models listed [here](https://huggingface.co/spaces/LiheYoung/Depth-Anything/tree/main/checkpoints) can provide relative depth estimation for any given image robustly. Please refer [here](#running) for details. @@ -188,7 +190,7 @@ depth = depth_anything(image) Easily use Depth Anything through [``transformers``](https://github.com/huggingface/transformers) within 3 lines of code! Please refer to [these instructions](https://huggingface.co/docs/transformers/main/model_doc/depth_anything) (credit to [@niels](https://huggingface.co/nielsr)). -**Note:** If you encounter ``KeyError: 'depth_anything'``, please install the latest ``transformers`` from source: +**Note:** If you encounter ``KeyError: 'depth_anything'``, please install the latest [``transformers``](https://github.com/huggingface/transformers) from source: ```bash pip install git+https://github.com/huggingface/transformers.git ``` @@ -210,13 +212,17 @@ depth = pipe(image)["depth"] **We sincerely appreciate all the extentions built on our Depth Anything from the community. Thank you a lot!** Here we list the extensions we have found: +- Depth Anything TensorRT: + - https://github.com/spacewalk01/depth-anything-tensorrt + - https://github.com/thinvy/DepthAnythingTensorrtDeploy + - https://github.com/daniel89710/trt-depth-anything - Depth Anything ONNX: https://github.com/fabio-sim/Depth-Anything-ONNX -- Depth Anything TensorRT: https://github.com/spacewalk01/depth-anything-tensorrt +- Depth Anything in Transformers.js (3D visualization): https://huggingface.co/spaces/Xenova/depth-anything-web +- Depth Anything for video (online demo): https://huggingface.co/spaces/JohanDL/Depth-Anything-Video - Depth Anything in ControlNet WebUI: https://github.com/Mikubill/sd-webui-controlnet - Depth Anything in ComfyUI's ControlNet: https://github.com/Fannovel16/comfyui_controlnet_aux - Depth Anything in X-AnyLabeling: https://github.com/CVHub520/X-AnyLabeling - Depth Anything in OpenXLab: https://openxlab.org.cn/apps/detail/yyfan/depth_anything -- Depth Anything in Transformers.js: https://huggingface.co/spaces/Xenova/depth-anything-web - Depth Anything in OpenVINO: https://github.com/openvinotoolkit/openvino_notebooks/tree/main/notebooks/280-depth-anything If you have your amazing projects supporting or improving (*e.g.*, speed) Depth Anything, please feel free to drop an issue. We will add them here. diff --git a/assets/gallery/nuscenes.gif b/assets/gallery/nuscenes.gif new file mode 100644 index 0000000..fe30720 Binary files /dev/null and b/assets/gallery/nuscenes.gif differ diff --git a/gallery.md b/gallery.md index 9309a64..43b35b0 100644 --- a/gallery.md +++ b/gallery.md @@ -114,7 +114,9 @@ You can click on the titles below to be directed to corresponding source pages. ## Video -The videos may be slow to load. Please wait a moment. +For more online showcases, please refer to https://twitter.com/WilliamLamkin/status/1755623301907460582. + +The videos below may be slow to load. Please wait a moment. ### [Racing game](https://twitter.com/i/status/1750683014152040853) @@ -124,6 +126,10 @@ The videos may be slow to load. Please wait a moment. +### [nuScenes](https://github.com/scepter914/DepthAnything-ROS) + + + ### [Indoor moving](https://twitter.com/PINTO03091/status/1750162506453041437) @@ -131,7 +137,7 @@ The videos may be slow to load. Please wait a moment. ## 3D -The videos may be slow to load. Please wait a moment. +The videos below may be slow to load. Please wait a moment. ### [3D visualization](https://twitter.com/victormustar/status/1753008143469093212) diff --git a/semseg/README.md b/semseg/README.md index 8e26f38..bb6beec 100644 --- a/semseg/README.md +++ b/semseg/README.md @@ -40,9 +40,7 @@ Note that our results are obtained *without* Mapillary pre-training. ## Installation -Please refer to [MMSegmentation](https://github.com/open-mmlab/mmsegmentation/blob/main/docs/en/get_started.md#installation) for instructions. - -Please also install mmdet to support Mask2Former: +Please refer to [MMSegmentation](https://github.com/open-mmlab/mmsegmentation/blob/main/docs/en/get_started.md#installation) for instructions. *Do not forget to install ``mmdet`` to support ``Mask2Former``:* ```bash pip install "mmdet>=3.0.0rc4" ``` @@ -52,7 +50,6 @@ After installation: - move our [dinov2.py](./dinov2.py) to mmseg's [backbones](https://github.com/open-mmlab/mmsegmentation/tree/main/mmseg/models/backbones) - add DINOv2 in mmseg's [models/backbones/\_\_init\_\_.py](https://github.com/open-mmlab/mmsegmentation/blob/main/mmseg/models/backbones/__init__.py) - download our provided [torchhub](https://github.com/LiheYoung/Depth-Anything/tree/main/torchhub) directory and put it at the root of your working directory - -**Note:** If you want to reproduce the **training** process, please 1) download the [Depth Anything pre-trained model](https://huggingface.co/spaces/LiheYoung/Depth-Anything/blob/main/checkpoints/depth_anything_vitl14.pth) (to initialize the encoder) and 2) put it under the ``checkpoints`` folder. +- download the [Depth Anything pre-trained model](https://huggingface.co/spaces/LiheYoung/Depth-Anything/blob/main/checkpoints/depth_anything_vitl14.pth) (to initialize the encoder) and 2) put it under the ``checkpoints`` folder. For training or inference with our pre-trained models, please refer to MMSegmentation [instructions](https://github.com/open-mmlab/mmsegmentation/blob/main/docs/en/user_guides/4_train_test.md).