Skip to content

[Fix] Update MMScan's README #99

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 4 commits into from
Feb 26, 2025
Merged

[Fix] Update MMScan's README #99

Show file tree
Hide file tree
Changes from 1 commit
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
0569df4
edit readme
rbler1234 Jan 24, 2025
8c0344a
edit readme
rbler1234 Jan 25, 2025
5677efa
edit readme
rbler1234 Jan 26, 2025
0ed18db
update readme
rbler1234 Feb 24, 2025
File filter

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
93 changes: 64 additions & 29 deletions README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -21,12 +21,14 @@

## 📋 Contents

1. [About](#-about)
2. [Getting Started](#-getting-started)
3. [Model and Benchmark](#-model-and-benchmark)
4. [TODO List](#-todo-list)
1. [About](#topic1)
2. [Getting Started](#topic2)
3. [MMScan API Tutorial](#topic3)
4. [MMScan Benchmark](#topic4)
5. [TODO List](#topic5)

## 🏠 About
<span id='topic1'/>

<!-- ![Teaser](assets/teaser.jpg) -->

Expand Down Expand Up @@ -55,7 +57,8 @@ Furthermore, we use this high-quality dataset to train state-of-the-art 3D visua
grounding and LLMs and obtain remarkable performance improvement both on
existing benchmarks and in-the-wild evaluation.

## 🚀 Getting Started:
## 🚀 Getting Started
<span id='topic2'/>

### Installation

Expand Down Expand Up @@ -98,6 +101,7 @@ existing benchmarks and in-the-wild evaluation.
Please refer to the [guide](data_preparation/README.md) here.

## 👓 MMScan API Tutorial
<span id='topic3'/>

The **MMScan Toolkit** provides comprehensive tools for dataset handling and model evaluation in tasks.

Expand Down Expand Up @@ -137,39 +141,41 @@ Each dataset item is a dictionary containing key elements:

(1) 3D Modality

- **"ori_pcds"** (tuple\[tensor\]): Raw point cloud data from the `.pth` file.
- **"pcds"** (np.ndarray): Point cloud data, dimensions (\[n_points, 6(xyz+rgb)\]).
- **"instance_labels"** (np.ndarray): Instance IDs for each point.
- **"class_labels"** (np.ndarray): Class IDs for each point.
- **"bboxes"** (dict): Bounding boxes in the scan.
- **"ori_pcds"** (tuple\[tensor\]): Original point cloud data extracted from the .pth file.
- **"pcds"** (np.ndarray): Point cloud data with dimensions [n_points, 6(xyz+rgb)], representing the coordinates and color of each point.
- **"instance_labels"** (np.ndarray): Instance ID assigned to each point in the point cloud.
- **"class_labels"** (np.ndarray): Class IDs assigned to each point in the point cloud.
- **"bboxes"** (dict): Information about bounding boxes within the scan.

(2) Language Modality

- **"sub_class"**: Sample category.
- **"ID"**: Unique sample ID.
- **"scan_id"**: Corresponding scan ID.
- **--------------For Visual Grounding Task**
- **"target_id"** (list\[int\]): IDs of target objects.
- **"text"** (str): Grounding text.
- **"sub_class"**: The sample category of the sample.
- **"ID"**: A unique identifier for the sample.
- **"scan_id"**:Identifier corresponding to the related scan.

*For Visual Grounding Task*
- **"target_id"** (list\[int\]): IDs of target objects.
- **"text"** (str): Text used for grounding.
- **"target"** (list\[str\]): Types of target objects.
- **"anchors"** (list\[str\]): Types of anchor objects.
- **"anchor_ids"** (list\[int\]): IDs of anchor objects.
- **"tokens_positive"** (dict): Position indices of mentioned objects in the text.
- **--------------ForQuestion Answering Task**
- **"question"** (str): The question text.
- **"tokens_positive"** (dict): Indices of positions where mentioned objects appear in the text.

*For Question Answering Task*
- **"question"** (str): The text of the question.
- **"answers"** (list\[str\]): List of possible answers.
- **"object_ids"** (list\[int\]): Object IDs referenced in the question.
- **"object_names"** (list\[str\]): Types of referenced objects.
- **"input_bboxes_id"** (list\[int\]): IDs of input bounding boxes.
- **"input_bboxes"** (list\[np.ndarray\]): Input bounding boxes, 9 DoF.
- **"input_bboxes"** (list\[np.ndarray\]): Input bounding box data, with 9 degrees of freedom.

(3) 2D Modality

- **'img_path'** (str): Path to RGB image.
- **'depth_img_path'** (str): Path to depth image.
- **'intrinsic'** (np.ndarray): Camera intrinsic parameters for RGB images.
- **'depth_intrinsic'** (np.ndarray): Camera intrinsic parameters for depth images.
- **'extrinsic'** (np.ndarray): Camera extrinsic parameters.
- **'img_path'** (str): File path to the RGB image.
- **'depth_img_path'** (str): File path to the depth image.
- **'intrinsic'** (np.ndarray): Intrinsic parameters of the camera for RGB images.
- **'depth_intrinsic'** (np.ndarray): Intrinsic parameters of the camera for Depth images.
- **'extrinsic'** (np.ndarray): Extrinsic parameters of the camera.
- **'visible_instance_id'** (list): IDs of visible objects in the image.

### MMScan Evaluator
Expand All @@ -182,7 +188,9 @@ For the visual grounding task, our evaluator computes multiple metrics including

- **AP and AR**: These metrics calculate the precision and recall by considering each sample as an individual category.
- **AP_C and AR_C**: These versions categorize samples belonging to the same subclass and calculate them together.
- **gtop-k**: An expanded metric that generalizes the traditional top-k metric, offering insights into broader performance aspects.
- **gTop-k**: An expanded metric that generalizes the traditional Top-k metric, offering insights into broader performance aspects.

*Note:* Here, AP corresponds to AP<sub>sample</sub> in the paper, and AP_C corresponds to AP<sub>box</sub> in the paper.

Below is an example of how to utilize the Visual Grounding Evaluator:

Expand Down Expand Up @@ -301,11 +309,38 @@ The input structure remains the same as for the question answering evaluator:
]
```

### Models
## 🏆 MMScan Benchmark

<span id='topic4'/>

### MMScan Visual Grounding Benchmark

We have adapted the MMScan API for some [models](./models/README.md).
| Methods | gTop-1 | gTop-3 | AP<sub>sample</sub> | AP<sub>box</sub> | AR | Release | Download |
|---------|--------|--------|---------------------|------------------|----|-------|----|
| ScanRefer | 4.74 | 9.19 | 9.49 | 2.28 | 47.68 | [code](https://github.com/rbler1234/EmbodiedScan/tree/mmscan-devkit/models/Scanrefer) | [model](https://drive.google.com/file/d/1C0-AJweXEc-cHTe9tLJ3Shgqyd44tXqY/view?usp=drive_link) \| [log](https://drive.google.com/file/d/1ENOS2FE7fkLPWjIf9J76VgiPrn6dGKvi/view?usp=drive_link) |
| MVT | 7.94 | 13.07 | 13.67 | 2.50 | 86.86 | ~ | ~ |
| BUTD-DETR | 15.24 | 20.68 | 18.58 | 9.27 | 66.62 | ~ | ~ |
| ReGround3D | 16.35 | 26.13 | 22.89 | 5.25 | 43.24 | ~ | ~ |
| EmbodiedScan | 19.66 | 34.00 | 29.30 | **15.18** | 59.96 | [code](https://github.com/OpenRobotLab/EmbodiedScan/tree/mmscan/models/EmbodiedScan) | [model](https://drive.google.com/file/d/1F6cHY6-JVzAk6xg5s61aTT-vD-eu_4DD/view?usp=drive_link) \| [log](https://drive.google.com/file/d/1Ua_-Z2G3g0CthbeBkrR1a7_sqg_Spd9s/view?usp=drive_link) |
| 3D-VisTA | 25.38 | 35.41 | 33.47 | 6.67 | 87.52 | ~ | ~ |
| ViL3DRef | **26.34** | **37.58** | **35.09** | 6.65 | 86.86 | ~ | ~ |

### MMScan Question Answering Benchmark
| Methods | Overall | ST-attr | ST-space | OO-attr | OO-space | OR| Advanced | Release | Download |
|---|--------|--------|--------|--------|--------|--------|-------|----|----|
| LL3DA | 45.7 | 39.1 | 58.5 | 43.6 | 55.9 | 37.1 | 24.0| [code](https://github.com/rbler1234/EmbodiedScan/tree/mmscan-devkit/models/LL3DA) | [model](https://drive.google.com/file/d/1mcWNHdfrhdbtySBtmG-QRH1Y1y5U3PDQ/view?usp=drive_link) \| [log](https://drive.google.com/file/d/1VHpcnO0QmAvMa0HuZa83TEjU6AiFrP42/view?usp=drive_link) |
| LEO |54.6 | 48.9 | 62.7 | 50.8 | 64.7 | 50.4 | 45.9 | [code](https://github.com/rbler1234/EmbodiedScan/tree/mmscan-devkit/models/LEO) | [model](https://drive.google.com/drive/folders/1HZ38LwRe-1Q_VxlWy8vqvImFjtQ_b9iA?usp=drive_link)|
| LLaVA-3D |**61.6** | 58.5 | 63.5 | 56.8 | 75.6 | 58.0 | 38.5|~ | ~ |

*Note:* These two tables only show the results for main metrics; see the paper for complete results.

We have released the codes of some models under [./models](./models/README.md).

## 📝 TODO List

- \[ \] More Visual Grounding baselines and Question Answering baselines.
<span id='topic5'/>

- \[ \] MMScan annotation and samples for ARKitScenes.
- \[ \] Online evaluation platform for the MMScan benchmark.
- \[ \] Codes of more MMScan Visual Grounding baselines and Question Answering baselines.
- \[ \] Full release and further updates.
21 changes: 20 additions & 1 deletion models/README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -21,7 +21,11 @@ These are 3D visual grounding models adapted for the mmscan-devkit. Currently, t
```bash
python -u scripts/train.py --use_color --eval_only --use_checkpoint "path/to/pth"
```
#### ckpts & Logs

| Epoch | gTop-1 @ 0.25/0.50 | Config | Download |
| :-------: | :---------: | :--------------------------------------------------------: | :--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------: |
| 50 | 4.74 / 2.52 | [config](https://drive.google.com/file/d/1iJtsjt4K8qhNikY8UmIfiQy1CzIaSgyU/view?usp=drive_link) | [model](https://drive.google.com/file/d/1C0-AJweXEc-cHTe9tLJ3Shgqyd44tXqY/view?usp=drive_link) \| [log](https://drive.google.com/file/d/1ENOS2FE7fkLPWjIf9J76VgiPrn6dGKvi/view?usp=drive_link)
### EmbodiedScan

1. Follow the [EmbodiedScan](https://github.com/OpenRobotLab/EmbodiedScan/blob/main/README.md) to setup the Env. Download the [Multi-View 3D Detection model's weights](https://download.openmmlab.com/mim-example/embodiedscan/mv-3ddet.pth) and change the "load_from" path in the config file under `configs/grounding` to the path where the weights are saved.
Expand All @@ -47,6 +51,11 @@ These are 3D visual grounding models adapted for the mmscan-devkit. Currently, t
# Multiple GPU testing
python tools/test.py configs/grounding/pcd_4xb24_mmscan_vg_num256.py path/to/load_pth --launcher="pytorch"
```
#### ckpts & Logs

| Input modality | Load pretrain | Epoch | gTop-1 @ 0.25/0.50 | Config | Download |
| :-------: | :----: | :----: | :---------: | :--------------------------------------------------------: | :--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------: |
| Point cloud | True | 12 | 19.66 / 8.82 | [config](https://github.com/rbler1234/EmbodiedScan/blob/mmscan-devkit/models/EmbodiedScan/configs/grounding/pcd_4xb24_mmscan_vg_num256.py) | [model](https://drive.google.com/file/d/1F6cHY6-JVzAk6xg5s61aTT-vD-eu_4DD/view?usp=drive_link) \| [log](https://drive.google.com/file/d/1Ua_-Z2G3g0CthbeBkrR1a7_sqg_Spd9s/view?usp=drive_link)

## 3D Question Answering Models

Expand Down Expand Up @@ -84,6 +93,13 @@ These are 3D question answering models adapted for the mmscan-devkit. Currently,
--tmp_path path/to/tmp --api_key your_api_key --eval_size -1
--nproc 4
```
#### ckpts & Logs

| Detector | Captioner | Iters | GPT score overall | Download |
| :-------: | :----: | :----: | :---------: |:--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------: |
| Vote2Cap-DETR | ll3da | 100k | 45.7 | [model](https://drive.google.com/file/d/1mcWNHdfrhdbtySBtmG-QRH1Y1y5U3PDQ/view?usp=drive_link) \| [log](https://drive.google.com/file/d/1VHpcnO0QmAvMa0HuZa83TEjU6AiFrP42/view?usp=drive_link) |



### LEO

Expand Down Expand Up @@ -117,5 +133,8 @@ These are 3D question answering models adapted for the mmscan-devkit. Currently,
--tmp_path path/to/tmp --api_key your_api_key --eval_size -1
--nproc 4
```
#### ckpts & Logs

PS : It is possible that LEO may encounter an "NaN" error in the MultiHeadAttentionSpatial module due to the training setup when training more epoches. ( no problem for 4GPU one epoch)
| LLM | 2d/3d backbones | epoch | GPT score overall | Config | Download |
| :-------: | :----: | :----: | :---------: | :--------------------------------------------------------: | :--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------: |
| Vicuna7b | ConvNeXt / PointNet++ | 1 | 54.6 | [config](https://drive.google.com/file/d/1CJccZd4TOaT_JdHj073UKwdA5PWUDtja/view?usp=drive_link) | [model](https://drive.google.com/drive/folders/1HZ38LwRe-1Q_VxlWy8vqvImFjtQ_b9iA?usp=drive_link) |
Loading