Add results for ICRA 2021 (nutonomy#623)

* Add results for ICRA 2021 * Add link to tracking leaderboard
yuesuLi · Jul 12, 2021 · 2c6a752 · 2c6a752
1 parent 57889ff
commit 2c6a752
Show file tree

Hide file tree

Showing 4 changed files with 36 additions and 0 deletions.
diff --git a/python-sdk/nuscenes/eval/detection/README.md b/python-sdk/nuscenes/eval/detection/README.md
@@ -47,6 +47,15 @@ The prizes will be awarded to submissions that outperform the previous state-of-
 Results and winners will be announced at [The AI Driving Olympics: Evaluating Progress in Robotics through Standardized and Reproducible Benchmarks](https://driving-olympics.ai/).
 Note that this challenge uses the same [evaluation server](https://eval.ai/web/challenges/challenge-page/356/overview) as previous detection challenges.
 
+A summary of the results can be seen below. 
+For details, please refer to the [detection leaderboard](https://www.nuscenes.org/object-detection).
+
+| Rank | Team name                             | NDS   | Award           |
+|---   |---                                    |---    |---              |
+|  1   | CenterPoint-Fusion and FusionPainting | 74.9% | Best submission |
+|  2   | PointAugmenting V2                    | 70.9% | -               |
+|  3   | Multimodal Virtual Point              | 70.5% | Most innovative |
+
 ### 5th AI Driving Olympics, NeurIPS 2020 
 The third nuScenes detection challenge will be held at [NeurIPS 2020](https://nips.cc/Conferences/2020/).
 Submissions will be accepted from November 1 to December 8, 2020.

diff --git a/python-sdk/nuscenes/eval/lidarseg/README.md b/python-sdk/nuscenes/eval/lidarseg/README.md
@@ -46,6 +46,15 @@ The prizes will be awarded to submissions that outperform the previous state-of-
 Results and winners will be announced at [The AI Driving Olympics: Evaluating Progress in Robotics through Standardized and Reproducible Benchmarks](https://driving-olympics.ai/).
 Note that this challenge uses the same [evaluation server](https://eval.ai/web/challenges/challenge-page/720/overview) as previous lidar segmentation challenges.
 
+A summary of the results can be seen below. 
+For details, please refer to the [lidar segmentation leaderboard](https://www.nuscenes.org/lidar-segmentation).
+
+| Rank | Team name          | mIOU  | Awards          |
+|---   |---                 |---    |---              |
+|  1   | SPVCNN++           | 0.811 | Best submission |
+|  2   | GU-Net             | 0.803 | -               |
+|  3   | 2D3DNet            | 0.800 | -               |
+
 ### 5th AI Driving Olympics, NeurIPS 2020
 The first nuScenes lidar segmentation challenge will be held at [NeurIPS 2020](https://nips.cc/Conferences/2020/).
 Submissions will be accepted from November 1 to December 8, 2020.

diff --git a/python-sdk/nuscenes/eval/prediction/README.md b/python-sdk/nuscenes/eval/prediction/README.md
@@ -43,6 +43,15 @@ The prizes will be awarded to submissions that outperform the previous state-of-
 Results and winners will be announced at [The AI Driving Olympics: Evaluating Progress in Robotics through Standardized and Reproducible Benchmarks](https://driving-olympics.ai/).
 Note that this challenge uses the same [evaluation server](https://eval.ai/web/challenges/challenge-page/591/overview) as previous prediction challenges.
 
+A summary of the results can be seen below. 
+For details, please refer to the [prediction leaderboard](https://www.nuscenes.org/prediction).
+
+| Rank | Team name    | minADE_5 | Awards          |
+|---   |---           |---       |---              |
+|  1   | P2T          | 1.45     | Best submission |
+|  2   | STSE         | 1.56     | -               |
+|  3   | SGNet        | 1.85     | -               |
+
 ### Workshop on Benchmarking Progress in Autonomous Driving, ICRA 2020
 The first nuScenes prediction challenge will be held at [ICRA 2020](https://www.icra2020.org/).
 This challenge will be focused on predicting trajectories for vehicles. The submission period will open April 1 and continue until May 28th, 2020.

diff --git a/python-sdk/nuscenes/eval/tracking/README.md b/python-sdk/nuscenes/eval/tracking/README.md
@@ -67,6 +67,15 @@ The prizes will be awarded to submissions that outperform the previous state-of-
 Results and winners will be announced at [The AI Driving Olympics: Evaluating Progress in Robotics through Standardized and Reproducible Benchmarks](https://driving-olympics.ai/).
 Note that this challenge uses the same [evaluation server](https://eval.ai/web/challenges/challenge-page/476/overview) as previous tracking challenges.
 
+A summary of the results can be seen below. 
+For details, please refer to the [tracking leaderboard](https://www.nuscenes.org/tracking).
+
+| Rank | Team name                    | AMOTA | Awards          |
+|---   |---                           |---    |---              |
+|  1   | MLPMOT and CBMOT+            | 68.1% | Best submission |
+|  2   | OGR3MOT                      | 65.6% | -               |
+|  3   | StanfordIPRL-TRI-Multi-Modal | 65.5% | -               |
+
 ### AI Driving Olympics (AIDO), NIPS 2019
 The first nuScenes tracking challenge will be held at NIPS 2019.
 Submission will open October 1 and close December 9.