Seal :seal:

December 16, 2023 · View on GitHub

Segment Any Point Cloud Sequences by Distilling Vision Foundation Models

Youquan Liu^1,*    Lingdong Kong^1,2,*    Jun Cen³    Runnan Chen⁴    Wenwei Zhang^1,5
Liang Pan⁵    Kai Chen¹    Ziwei Liu⁵
¹Shanghai AI Laboratory    ²National University of Singapore    ³The Hong Kong University of Science and Technology    ⁴The University of Hong Kong    ⁵S-Lab, Nanyang Technological University

Seal :seal:

Seal is a versatile self-supervised learning framework capable of segmenting any automotive point clouds by leveraging off-the-shelf knowledge from vision foundation models (VFMs) and encouraging spatial and temporal consistency from such knowledge during the representation learning stage.

:sparkles: Highlight

:rocket: Scalability: Seal directly distills the knowledge from VFMs into point clouds, eliminating the need for annotations in either 2D or 3D during pretraining.
:balance_scale: Consistency: Seal enforces the spatial and temporal relationships at both the camera-to-LiDAR and point-to-segment stages, facilitating cross-modal representation learning.
:rainbow: Generalizability: Seal enables knowledge transfer in an off-the-shelf manner to downstream tasks involving diverse point clouds, including those from real/synthetic, low/high-resolution, large/small-scale, and clean/corrupted datasets.

:oncoming_automobile: 2D-3D Correspondence

:movie_camera: Video Demo

Demo 1	Demo 2	Demo 3

Link ^{:arrow_heading_up:}	Link ^{:arrow_heading_up:}	Link ^{:arrow_heading_up:}

Updates

[2023.12] - We are hosting The RoboDrive Challenge at ICRA 2024. :blue_car:
[2023.09] - Seal was selected as a :sparkles: spotlight :sparkles: at NeurIPS 2023.
[2023.09] - Seal was accepted to NeurIPS 2023! :tada:
[2023.07] - We release the code for generating semantic superpixel & superpoint by SLIC, SAM, and SEEM. More VFMs coming on the way!
[2023.06] - Our paper is available on arXiv, click here to check it out. Code will be available later!

Installation

Please refer to INSTALL.md for the installation details.

Data Preparation

nuScenes	SemanticKITTI	Waymo Open	ScribbleKITTI

RELLIS-3D	SemanticPOSS	SemanticSTF	DAPS-3D

SynLiDAR	Synth4D	nuScenes-C

Please refer to DATA_PREPARE.md for the details to prepare these datasets.

Superpoint Generation

Raw Point Cloud	Semantic Superpoint	Groundtruth

Kindly refer to SUPERPOINT.md for the details to generate the semantic superpixels & superpoints with vision foundation models.

Getting Started

Kindly refer to GET_STARTED.md to learn more usage of this codebase.

Main Result

:unicorn: Framework Overview


Overview of the Seal :seal: framework. We generate, for each {LiDAR, camera} pair at timestamp t and another LiDAR frame at timestamp t + n, the semantic superpixel and superpoint by VFMs. Two pertaining objectives are then formed, including spatial contrastive learning between paired LiDAR and camera features and temporal consistency regularization between segments at different timestamps.

Overview of the Seal :seal: framework. We generate, for each {LiDAR, camera} pair at timestamp t and another LiDAR frame at timestamp t + n, the semantic superpixel and superpoint by VFMs. Two pertaining objectives are then formed, including spatial contrastive learning between paired LiDAR and camera features and temporal consistency regularization between segments at different timestamps.

:car: Cosine Similarity


The cosine similarity between a query point (red dot) and the feature learned with SLIC and different VFMs in our Seal :seal: framework. The queried semantic classes from top to bottom examples are: “car”, “manmade”, and “truck”. The color goes from violet to yellow denoting low and high similarity scores, respectively.

:blue_car: Benchmark

Method	nuScenes						KITTI	Waymo	Synth4D
Method	LP	1%	5%	10%	25%	Full	1%	1%	1%
Random	8.10	30.30	47.84	56.15	65.48	74.66	39.50	39.41	20.22
PointContrast	21.90	32.50	-	-	-	-	41.10	-	-
DepthContrast	22.10	31.70	-	-	-	-	41.50	-	-
PPKT	35.90	37.80	53.74	60.25	67.14	74.52	44.00	47.60	61.10
SLidR	38.80	38.30	52.49	59.84	66.91	74.79	44.60	47.12	63.10
ST-SLidR	40.48	40.75	54.69	60.75	67.70	75.14	44.72	44.93	-
Seal :seal:	44.95	45.84	55.64	62.97	68.41	75.60	46.63	49.34	64.50

:bus: Linear Probing


The qualitative results of our Seal :seal: framework pretrained on nuScenes (without using groundtruth labels) and linear probed with a frozen backbone and a linear classification head. To highlight the differences, the correct / incorrect predictions are painted in gray / red, respectively.

:articulated_lorry: Downstream Generalization

Method	ScribbleKITTI		RELLIS-3D		SemanticPOSS		SemanticSTF		SynLiDAR		DAPS-3D
Method	1%	10%	1%	10%	Half	Full	Half	Full	1%	10%	Half	Full
Random	23.81	47.60	38.46	53.60	46.26	54.12	48.03	48.15	19.89	44.74	74.32	79.38
PPKT	36.50	51.67	49.71	54.33	50.18	56.00	50.92	54.69	37.57	46.48	78.90	84.00
SLidR	39.60	50.45	49.75	54.57	51.56	55.36	52.01	54.35	42.05	47.84	81.00	85.40
Seal :seal:	40.64	52.77	51.09	55.03	53.26	56.89	53.46	55.36	43.58	49.26	81.88	85.90

:truck: Robustness Probing

Init	Backbone	mCE	mRR	Fog	Wet	Snow	Motion	Beam	Cross	Echo	Sensor
Random	PolarNet	115.09	76.34	58.23	69.91	64.82	44.60	61.91	40.77	53.64	42.01
Random	CENet	112.79	76.04	67.01	69.87	61.64	58.31	49.97	60.89	53.31	24.78
Random	WaffleIron	106.73	72.78	56.07	73.93	49.59	59.46	65.19	33.12	61.51	44.01
Random	Cylinder3D	105.56	78.08	61.42	71.02	58.40	56.02	64.15	45.36	59.97	43.03
Random	SPVCNN	106.65	74.70	59.01	72.46	41.08	58.36	65.36	36.83	62.29	49.21
Random	MinkUNet	112.20	72.57	62.96	70.65	55.48	51.71	62.01	31.56	59.64	39.41
PPKT	MinkUNet	105.64	76.06	64.01	72.18	59.08	57.17	63.88	36.34	60.59	39.57
SLidR	MinkUNet	106.08	75.99	65.41	72.31	56.01	56.07	62.87	41.94	61.16	38.90
Seal :seal:	MinkUNet	92.63	83.08	72.66	74.31	66.22	66.14	65.96	57.44	59.87	39.85

:tractor: Qualitative Assessment


The qualitative results of Seal :seal: and prior methods pretrained on nuScenes (without using groundtruth labels) and fine-tuned with 1% labeled data. To highlight the differences, the correct / incorrect predictions are painted in gray / red, respectively.

TODO List

Initial release. :rocket:
Add license. See here for more details.
Add video demos :movie_camera:
Add installation details.
Add data preparation details.
Support semantic superpixel generation.
Support semantic superpoint generation.
Add evaluation details.
Add training details.

Citation

If you find this work helpful, please kindly consider citing our paper:

@inproceedings{liu2023segment,
  title = {Segment Any Point Cloud Sequences by Distilling Vision Foundation Models},
  author = {Liu, Youquan and Kong, Lingdong and Cen, Jun and Chen, Runnan and Zhang, Wenwei and Pan, Liang and Chen, Kai and Liu, Ziwei},
  booktitle = {Advances in Neural Information Processing Systems}, 
  year = {2023},
}

@misc{liu2023segment_any_point_cloud,
  title = {The Segment Any Point Cloud Codebase},
  author = {Liu, Youquan and Kong, Lingdong and Cen, Jun and Chen, Runnan and Zhang, Wenwei and Pan, Liang and Chen, Kai and Liu, Ziwei},
  howpublished = {\url{https://github.com/youquanl/Segment-Any-Point-Cloud}},
  year = {2023},
}

License

This work is under the Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.

Acknowledgement

This work is developed based on the MMDetection3D codebase.

MMDetection3D is an open-source object detection toolbox based on PyTorch, towards the next-generation platform for general 3D detection. It is a part of the OpenMMLab project developed by MMLab.

Part of this codebase has been adapted from SLidR, Segment Anything, X-Decoder, OpenSeeD, Segment Everything Everywhere All at Once, LaserMix, and Robo3D.

:heart: We thank the exceptional contributions from the above open-source repositories!