Roadmap of MMDetection3d #16

hellock · 2020-07-13T13:33:41Z

We keep this issue open to collect feature requests from users and hear your voice. Our monthly release plan is also available here.

You can either:

Suggest a new feature by leaving a comment.
Vote for a feature request with 👍 or be against with 👎. (Remember that developers are busy and cannot respond to all feature requests, so vote for your most favorable one!)
Tell us that you would like to help implement one of the features in the list or review the PRs. (This is the greatest things to hear about!)

V0.7.0 (October-November)

Switch visualization backend to Open3D
More performance on Waymo, nuScenes, SUN RGB-D, and ScanNet dataset

V0.6.0 (September)

Waymo Dataset (Bump to V0.6.0 #118)
Batch Inference ([Fix]: fix multi-batch test problem #95)
CenterPoint (Add mg_head #49, Centerpoint config detector #92)
3DSSD ([feature]: support ssd_3d_head in 3DSSD #83, [fix]:3dssd-config #100, [feature] add 3dssd benchmark #104)
H3DNet (add primitive head #53, add h3d head #58, [fix]: fix bug of H3DNet config #105)

turboxin · 2020-07-15T05:40:08Z

Hi all, thanks for releasing this wonderful project！

I 'm wondering what's your recent development plan for new models or methods?

thuyngch · 2020-07-15T13:33:22Z

In the previous version (PCDet), I see that PV-RCNN is supported. However, it is not supported now. So, I hope to see PV-RCNN again.

hellock · 2020-07-15T13:59:11Z

In the previous version (PCDet), I see that PV-RCNN is supported. However, it is not supported now. So, I hope to see PV-RCNN again.

PCDet and mmdet3d are two different codebases. You may refer to PCDet for PV-RCNN now, and we will support it in mmdet3d soon.

SilvioGiancola · 2020-07-20T11:51:15Z

Thanks for the development of MMDetection3d. I would appreciate the support for the Waymo Dataset.

chuong98 · 2020-07-21T06:50:22Z

Thanks for the opensource. Can we support 3DSSD https://github.com/Jia-Research-Lab/3DSSD?
It seems achieve both good speed and high AP.
Thank you.

zehanzhang · 2020-08-21T06:14:26Z

Can we support SA-SSD https://github.com/skyhehe123/SA-SSD？The AP and speed is also good.

hhcNWPU · 2020-09-05T13:59:16Z

Hello, this code can visualize the 3D detection box in the point cloud, may I ask if the 3D detection box can be visualized in the 2D image，and how do we do that?

linchunmian · 2020-09-17T01:30:50Z

Hi. all. I hope to see the implementation of pseudo LiDAR in mmdetection3d. And also, I think more visualization of data processing and detection result are required, too.
Thanks.

AllenPeng0209 · 2020-10-12T02:01:16Z

Hi, all.
the current strongest backbone SPVNAS could be a good thing to implement.
Also, it's new library torchsparse is much faster than the current library.

https://github.com/mit-han-lab/torchsparse
https://github.com/mit-han-lab/e3d/blob/master/spvnas/core/models/semantic_kitti/spvnas.py

PersistentXQ · 2020-10-19T02:02:01Z

Hi, all. If I wanna add a feature to dataset (for example, besides (x,y,z,intensity), I wanna add another feature to it and make the data become (x,y,z,intensity,another featrue).), could you guys provides some interfaces or functions or sth?

ZwwWayne · 2020-10-19T13:40:42Z

Hi, all. If I wanna add a feature to dataset (for example, besides (x,y,z,intensity), I wanna add another feature to it and make the data become (x,y,z,intensity,another featrue).), could you guys provides some interfaces or functions or sth?

We recommend to do this in the model part. You can implement a new module to process the point data following the guide here

PersistentXQ · 2020-10-20T06:53:07Z

Hi, all. If I wanna add a feature to dataset (for example, besides (x,y,z,intensity), I wanna add another feature to it and make the data become (x,y,z,intensity,another featrue).), could you guys provides some interfaces or functions or sth?

We recommend to do this in the model part. You can implement a new module to process the point data following the guide here

ZwwWayne, thank you very much for your answer. I think I asked a wrong question… The new kitti-like dataset (x,y,z,intensity,another feature) have already been made. The question is how I can train the model with my dataset. I tried to change the "load_dims" and "use_dims" in configs from 4 to 5, but some errors were threw… After I fixed these errors, another errors were threw again… Now the newest error is Runtime Error: size mismatch.

ZwwWayne · 2020-10-20T12:13:28Z

Hi, all. If I wanna add a feature to dataset (for example, besides (x,y,z,intensity), I wanna add another feature to it and make the data become (x,y,z,intensity,another featrue).), could you guys provides some interfaces or functions or sth?

We recommend to do this in the model part. You can implement a new module to process the point data following the guide here

ZwwWayne, thank you very much for your answer. I think I asked a wrong question… The new kitti-like dataset (x,y,z,intensity,another feature) have already been made. The question is how I can train the model with my dataset. I tried to change the "load_dims" and "use_dims" in configs from 4 to 5, but some errors were threw… After I fixed these errors, another errors were threw again… Now the newest error is Runtime Error: size mismatch.

Feel free to create a new issue to describe your issues following the reimplementation issues template if you need some help. This issue is mainly about the roadmap.

ZwwWayne · 2020-10-20T12:14:23Z

Hi, all.
the current strongest backbone SPVNAS could be a good thing to implement.
Also, it's new library torchsparse is must faster than the current library.

https://github.com/mit-han-lab/torchsparse
https://github.com/mit-han-lab/e3d/blob/master/spvnas/core/models/semantic_kitti/spvnas.py

Thanks for the suggestion. We will investigate these repos and may change the dependency if necessary.

YoushaaMurhij · 2020-11-04T15:40:20Z

Can you add support for sematic-kitti ?

chasingw · 2020-11-17T06:34:14Z

any plan for ONNX support?

ZwwWayne · 2020-11-22T03:33:20Z

any plan for ONNX support?

This is a planned feature, but we may not support it very soon. So PRs are also welcomed.

qinsimon · 2020-11-30T05:43:27Z

Thanks for your job. And it would be nice if cuda11.1/torch1.7 are compatible

chakri1804 · 2020-12-23T10:53:17Z

Can you add support for Pandaset ?

filaPro · 2021-01-02T12:24:02Z

Do you have plans to release the code for your FCOS3D on NuScenes in near future?

Tai-Wang · 2021-01-02T12:27:31Z

Do you have plans to release the code for your FCOS3D on NuScenes in near future?

Yes. More information could be referred to #247 .

Jsijon · 2021-01-31T17:10:13Z

Can you support Cirrus dataset ?
https://arxiv.org/abs/2012.02938

Wuziyi616 · 2021-04-19T14:51:28Z

Hello, this code can visualize the 3D detection box in the point cloud, may I ask if the 3D detection box can be visualized in the 2D image，and how do we do that?

Hi, this multi-modality visualization has been supported recently. Check out our demo and how to use for it!

poddar414 · 2022-05-24T06:24:08Z

pointPainting

PersistentXQ · 2022-05-24T06:24:28Z

这是来自QQ邮箱的自动回复邮件。您好，您的来信已收到，我将尽快给您回复。徐谦

nacayu · 2022-06-16T08:50:43Z

It would be nice if mmdet3d could incorporate radar information like lidar, Our lab, and many radar researcher also need a good platform to employ radar and camera fusion and so on, thanks.

PersistentXQ · 2022-06-16T08:51:03Z

这是来自QQ邮箱的自动回复邮件。您好，您的来信已收到，我将尽快给您回复。徐谦

xiaoyangyang123 · 2022-07-17T02:47:31Z

你好，请问dgcnn的内容是删除了嘛？什么时候重新上线呢？

PersistentXQ · 2022-07-17T02:47:55Z

这是来自QQ邮箱的自动回复邮件。您好，您的来信已收到，我将尽快给您回复。徐谦

sxfzzz · 2022-08-06T17:20:30Z

Would you consider RPVNet?
RPVNet: A Deep and Efficient Range-Point-Voxel Fusion Network for LiDAR Point Cloud Segmentation

PersistentXQ · 2022-08-06T17:20:51Z

这是来自Foxmail邮箱的自动回复邮件。您好，您的来信已收到，我将尽快给您回复。徐谦

xiaoyangyang123 · 2022-08-13T02:45:54Z

你会考虑RPVNet吗？ RPVNet：用于激光雷达点云分段的深度高效范围-点-体素融合网络

有考虑用point transformer进行尝试，您说的这个我还没有细看。主要是想将新内容用在dgcnn上进行尝试提升，不知您有什么好的建议？

* add trt instance norm plugin * last line empty * fix clang format * fix grid_sample clang format * remove redundant * fix lint * refine codes * fix clang format * clang format * clang format * clang format

* support coverage * test codecov action 2

CarlHuangNuc · 2022-10-28T21:51:26Z

deep fusion and bevfusion

PersistentXQ · 2022-10-28T21:51:53Z

这是来自Foxmail邮箱的自动回复邮件。您好，您的来信已收到，我将尽快给您回复。

YoushaaMurhij · 2023-01-18T18:39:28Z

Support radar data in nuScenes!

PersistentXQ · 2023-01-18T18:39:48Z

这是来自Foxmail邮箱的自动回复邮件。您好，您的来信已收到，我将尽快给您回复。

zhanghang1989 · 2023-02-06T16:39:56Z

Suggested by @JingweiZhang12 . Add request for Cube RCNN implementation.
It would be great if mmdetection3d could support Cube RCNN from Omni3d paper, so that we can easily compare across different method.

PersistentXQ · 2023-02-06T16:40:18Z

这是来自Foxmail邮箱的自动回复邮件。您好，您的来信已收到，我将尽快给您回复。

schneidersebastian · 2023-02-06T19:02:24Z

It would be nice if mmdet3d could incorporate radar information like lidar, Our lab, and many radar researcher also need a good platform to employ radar and camera fusion and so on, thanks.

Any updates on that?

aFickle · 2023-10-28T09:31:17Z

为什么我就是实现不了目标检测的demo，谁能帮帮我

PersistentXQ · 2023-10-28T09:31:41Z

这是来自Foxmail邮箱的自动回复邮件。您好，您的来信已收到，我将尽快给您回复。

gorkemguzeler · 2024-10-23T11:53:03Z

It would be nice if mmdet3d could incorporate radar information like lidar, Our lab, and many radar researcher also need a good platform to employ radar and camera fusion and so on, thanks.

Hi, is there any update on the radar integration for bevfusion project?

PersistentXQ · 2024-10-23T11:53:39Z

这是来自Foxmail邮箱的自动回复邮件。您好，您的来信已收到，我将尽快给您回复。

mason1008 · 2024-10-28T15:01:29Z

@JingweiZhang12 @zhanghang1989
Is there any recent progress on the implementation of Cube R-CNN in MMDetection3D?

hellock added community help wanted Need help from community good first issue Good for newcomers labels Jul 13, 2020

hellock pinned this issue Jul 13, 2020

xavierwu95 mentioned this issue Sep 16, 2020

corresponding relationship between data and model architecture #108

Closed

ZwwWayne closed this as completed Nov 5, 2020

ZwwWayne reopened this Nov 5, 2020

lji72 mentioned this issue Apr 15, 2021

ImvoteNet 2-stage model reproduce error #448

Closed

tpoisonooo pushed a commit to tpoisonooo/mmdetection3d that referenced this issue Sep 5, 2022

[Enhancement] support coverage (open-mmlab#16)

f693f7c

* support coverage * test codecov action 2

JingweiZhang12 mentioned this issue Dec 21, 2022

Does MMDet3D support binocular method？Thank you！ #2156

Open

JingweiZhang12 mentioned this issue Feb 6, 2023

Any Plan to Support Cube RCNN? #2255

Open

2 tasks

JingweiZhang12 mentioned this issue Feb 16, 2023

[Feature] Support aiMotive dataset #2284

Open

mendoza-G mentioned this issue Mar 13, 2023

[Bug] CUDA error: an illegal memory access was encountered when training MVX-NET kitti #2209

Open

3 tasks

jumptiger66 mentioned this issue Apr 25, 2023

Setting --gpu-id 3 when i train ScanNet on Votenet ，i got error #2471

Closed

Xiangxu-0103 unpinned this issue Jul 5, 2023

Xiangxu-0103 pinned this issue Jul 5, 2023

Roadmap of MMDetection3d #16

Roadmap of MMDetection3d #16

Comments

hellock commented Jul 13, 2020 • edited by ZwwWayne Loading

V0.7.0 (October-November)

V0.6.0 (September)

turboxin commented Jul 15, 2020

thuyngch commented Jul 15, 2020

hellock commented Jul 15, 2020

SilvioGiancola commented Jul 20, 2020

chuong98 commented Jul 21, 2020

zehanzhang commented Aug 21, 2020

hhcNWPU commented Sep 5, 2020

linchunmian commented Sep 17, 2020

AllenPeng0209 commented Oct 12, 2020 • edited Loading

PersistentXQ commented Oct 19, 2020

ZwwWayne commented Oct 19, 2020

PersistentXQ commented Oct 20, 2020

ZwwWayne commented Oct 20, 2020

ZwwWayne commented Oct 20, 2020

YoushaaMurhij commented Nov 4, 2020

chasingw commented Nov 17, 2020

ZwwWayne commented Nov 22, 2020

qinsimon commented Nov 30, 2020

chakri1804 commented Dec 23, 2020

filaPro commented Jan 2, 2021

Tai-Wang commented Jan 2, 2021

Jsijon commented Jan 31, 2021

Wuziyi616 commented Apr 19, 2021

poddar414 commented May 24, 2022

PersistentXQ commented May 24, 2022 via email

nacayu commented Jun 16, 2022

PersistentXQ commented Jun 16, 2022 via email

xiaoyangyang123 commented Jul 17, 2022

PersistentXQ commented Jul 17, 2022 via email

sxfzzz commented Aug 6, 2022

PersistentXQ commented Aug 6, 2022 via email

xiaoyangyang123 commented Aug 13, 2022

CarlHuangNuc commented Oct 28, 2022

PersistentXQ commented Oct 28, 2022 via email

YoushaaMurhij commented Jan 18, 2023

PersistentXQ commented Jan 18, 2023 via email

zhanghang1989 commented Feb 6, 2023

PersistentXQ commented Feb 6, 2023 via email

schneidersebastian commented Feb 6, 2023

aFickle commented Oct 28, 2023

PersistentXQ commented Oct 28, 2023 via email

gorkemguzeler commented Oct 23, 2024

PersistentXQ commented Oct 23, 2024 via email

mason1008 commented Oct 28, 2024

hellock commented Jul 13, 2020 •

edited by ZwwWayne

Loading

AllenPeng0209 commented Oct 12, 2020 •

edited

Loading