{ "id": 177113, "title": "Research Papers", "url": "/competitions/lyft-motion-prediction-autonomous-vehicles/discussion/177113", "author_name": "", "post_date": "2020-08-24T22:15:19.561393100Z", "votes": 29, "comment_count": 5, "views": 0, "content": "", "messages": [ { "id": "984155", "postDate": "08/24/2020 22:15:19", "content": "", "rawMarkdown": "* Deep Learning-based Vehicle Behaviour Prediction for Autonomous Driving Applications: [a Review](https://arxiv.org/pdf/1912.11676.pdf)", "votes": null }, { "id": "984321", "postDate": "08/25/2020 03:24:48", "content": "

Just found a list of papers from CVPR2019 related to Autonomous Driving. If you find any of them are useful, please add them to your list
\n1、Pseudo-LiDAR from Visual Depth Estimation: Bridging the Gap in 3D Object Detection for Autonomous Driving
\nhttps://arxiv.org/abs/1812.07179
\nhttps://github.com/mileyan/pseudo_lidar
\n2、ApolloCar3D: A Large 3D Car Instance Understanding Benchmark for Autonomous Driving
\nhttps://arxiv.org/abs/1811.12222
\n3、Group-wise Correlation Stereo Network
\nhttps://arxiv.org/abs/1903.04025
\n4、Stereo R-CNN based 3D Object Detection for Autonomous Driving
\nhttps://arxiv.org/abs/1902.09738
\n5、Deep Rigid Instance Scene Flow
\nhttps://people.csail.mit.edu/weichium/papers/cvpr19-dsisf/paper.pdf
\n6、An Efficient Schmidt-EKF for 3D visual-inertial SLAM
\nhttps://arxiv.org/abs/1903.08636
\n7、LaserNet: An Efficient Probabilistic 3D Object Detector for Autonomous Driving
\nGregory P. Meyer, Ankit Laddha, Eric Kee, Carlos Vallespi-Gonzalez, Carl K. Wellington
\nhttps://arxiv.org/abs/1903.08701
\n8、.GS3D: An Efficient 3D Object Detection Framework for Autonomous Driving
\nhttps://arxiv.org/abs/1903.10955
\n9、Learning to Adapt for Stereo
\nhttps://arxiv.org/abs/1904.02957
\nhttps://github.com/CVLAB-Unibo/Learning2AdaptForStereo
\n10、What Object Should I Use? - Task Driven Object Detection
\nhttps://arxiv.org/abs/1904.03000
\n11、YUVMultiNet: Real-time YUV multi-task CNN for autonomous driving
\nhttps://arxiv.org/abs/1904.05673
\n12、L3-Net: Towards Learning-based LiDAR Localization for Autonomous Driving
\nhttps://songshiyu01.github.io/pdf/L3Net_W.Lu_Y.Zhou_S.Song_CVPR2019.pdf

", "rawMarkdown": "Just found a list of papers from CVPR2019 related to Autonomous Driving. If you find any of them are useful, please add them to your list\n1、Pseudo-LiDAR from Visual Depth Estimation: Bridging the Gap in 3D Object Detection for Autonomous Driving\nhttps://arxiv.org/abs/1812.07179\nhttps://github.com/mileyan/pseudo_lidar\n2、ApolloCar3D: A Large 3D Car Instance Understanding Benchmark for Autonomous Driving\nhttps://arxiv.org/abs/1811.12222\n3、Group-wise Correlation Stereo Network\nhttps://arxiv.org/abs/1903.04025\n4、Stereo R-CNN based 3D Object Detection for Autonomous Driving\nhttps://arxiv.org/abs/1902.09738\n5、Deep Rigid Instance Scene Flow\nhttps://people.csail.mit.edu/weichium/papers/cvpr19-dsisf/paper.pdf\n6、An Efficient Schmidt-EKF for 3D visual-inertial SLAM\nhttps://arxiv.org/abs/1903.08636\n7、LaserNet: An Efficient Probabilistic 3D Object Detector for Autonomous Driving\nGregory P. Meyer, Ankit Laddha, Eric Kee, Carlos Vallespi-Gonzalez, Carl K. Wellington\nhttps://arxiv.org/abs/1903.08701\n8、.GS3D: An Efficient 3D Object Detection Framework for Autonomous Driving\nhttps://arxiv.org/abs/1903.10955\n9、Learning to Adapt for Stereo\nhttps://arxiv.org/abs/1904.02957\nhttps://github.com/CVLAB-Unibo/Learning2AdaptForStereo\n10、What Object Should I Use? - Task Driven Object Detection\nhttps://arxiv.org/abs/1904.03000\n11、YUVMultiNet: Real-time YUV multi-task CNN for autonomous driving\nhttps://arxiv.org/abs/1904.05673\n12、L3-Net: Towards Learning-based LiDAR Localization for Autonomous Driving\nhttps://songshiyu01.github.io/pdf/L3Net_W.Lu_Y.Zhou_S.Song_CVPR2019.pdf", "votes": null }, { "id": "984447", "postDate": "08/25/2020 05:20:48", "content": "

thanks for share

", "rawMarkdown": "thanks for share", "votes": null }, { "id": "984958", "postDate": "08/25/2020 11:48:16", "content": "

Here are all the papers with code from the CVPR 2020:
\nhttps://paperswithcode.com/conference/cvpr-2020-6

", "rawMarkdown": "Here are all the papers with code from the CVPR 2020:\nhttps://paperswithcode.com/conference/cvpr-2020-6", "votes": null }, { "id": "985465", "postDate": "08/25/2020 18:34:30", "content": "

If you're looking for SOTA on behavior prediction, there are some new papers coming out. Also, it can be overwhelming to read a long list of papers. The following papers I've seen to be picked as baselines for SOTA comparison,

\n

Covernet https://arxiv.org/pdf/1911.10298.pdf
\nMultipath https://arxiv.org/pdf/1910.05449.pdf
\nMTP https://arxiv.org/abs/1809.10732
\nSpaGNN https://arxiv.org/pdf/1910.08233.pdf (this one is joint perception & prediction however, the idea around prediction can be reused)

", "rawMarkdown": "If you're looking for SOTA on behavior prediction, there are some new papers coming out. Also, it can be overwhelming to read a long list of papers. The following papers I've seen to be picked as baselines for SOTA comparison,\n\nCovernet https://arxiv.org/pdf/1911.10298.pdf\nMultipath https://arxiv.org/pdf/1910.05449.pdf\nMTP https://arxiv.org/abs/1809.10732\nSpaGNN https://arxiv.org/pdf/1910.08233.pdf (this one is joint perception & prediction however, the idea around prediction can be reused)", "votes": null }, { "id": "1002636", "postDate": "09/08/2020 09:50:13", "content": "

I had a look also at a citing review that addresses the topic of video prediction, that I am trying to apply to the Lyft challenge. Very good explanation of the basics

\n

https://arxiv.org/pdf/2004.05214.pdf

", "rawMarkdown": "I had a look also at a citing review that addresses the topic of video prediction, that I am trying to apply to the Lyft challenge. Very good explanation of the basics\n\n https://arxiv.org/pdf/2004.05214.pdf", "votes": null } ], "comments": [ { "id": 984321, "author_name": "kehanwang1998", "author_url": "", "post_date": "08/25/2020 03:24:48", "content": "

Just found a list of papers from CVPR2019 related to Autonomous Driving. If you find any of them are useful, please add them to your list
\n1、Pseudo-LiDAR from Visual Depth Estimation: Bridging the Gap in 3D Object Detection for Autonomous Driving
\nhttps://arxiv.org/abs/1812.07179
\nhttps://github.com/mileyan/pseudo_lidar
\n2、ApolloCar3D: A Large 3D Car Instance Understanding Benchmark for Autonomous Driving
\nhttps://arxiv.org/abs/1811.12222
\n3、Group-wise Correlation Stereo Network
\nhttps://arxiv.org/abs/1903.04025
\n4、Stereo R-CNN based 3D Object Detection for Autonomous Driving
\nhttps://arxiv.org/abs/1902.09738
\n5、Deep Rigid Instance Scene Flow
\nhttps://people.csail.mit.edu/weichium/papers/cvpr19-dsisf/paper.pdf
\n6、An Efficient Schmidt-EKF for 3D visual-inertial SLAM
\nhttps://arxiv.org/abs/1903.08636
\n7、LaserNet: An Efficient Probabilistic 3D Object Detector for Autonomous Driving
\nGregory P. Meyer, Ankit Laddha, Eric Kee, Carlos Vallespi-Gonzalez, Carl K. Wellington
\nhttps://arxiv.org/abs/1903.08701
\n8、.GS3D: An Efficient 3D Object Detection Framework for Autonomous Driving
\nhttps://arxiv.org/abs/1903.10955
\n9、Learning to Adapt for Stereo
\nhttps://arxiv.org/abs/1904.02957
\nhttps://github.com/CVLAB-Unibo/Learning2AdaptForStereo
\n10、What Object Should I Use? - Task Driven Object Detection
\nhttps://arxiv.org/abs/1904.03000
\n11、YUVMultiNet: Real-time YUV multi-task CNN for autonomous driving
\nhttps://arxiv.org/abs/1904.05673
\n12、L3-Net: Towards Learning-based LiDAR Localization for Autonomous Driving
\nhttps://songshiyu01.github.io/pdf/L3Net_W.Lu_Y.Zhou_S.Song_CVPR2019.pdf

", "votes": null, "replies": [] }, { "id": 984447, "author_name": "singhakash", "author_url": "", "post_date": "08/25/2020 05:20:48", "content": "

thanks for share

", "votes": null, "replies": [] }, { "id": 984958, "author_name": "crained", "author_url": "", "post_date": "08/25/2020 11:48:16", "content": "

Here are all the papers with code from the CVPR 2020:
\nhttps://paperswithcode.com/conference/cvpr-2020-6

", "votes": null, "replies": [] }, { "id": 985465, "author_name": "t3nyks", "author_url": "", "post_date": "08/25/2020 18:34:30", "content": "

If you're looking for SOTA on behavior prediction, there are some new papers coming out. Also, it can be overwhelming to read a long list of papers. The following papers I've seen to be picked as baselines for SOTA comparison,

\n

Covernet https://arxiv.org/pdf/1911.10298.pdf
\nMultipath https://arxiv.org/pdf/1910.05449.pdf
\nMTP https://arxiv.org/abs/1809.10732
\nSpaGNN https://arxiv.org/pdf/1910.08233.pdf (this one is joint perception & prediction however, the idea around prediction can be reused)

", "votes": null, "replies": [] }, { "id": 1002636, "author_name": "mclikmb4", "author_url": "", "post_date": "09/08/2020 09:50:13", "content": "

I had a look also at a citing review that addresses the topic of video prediction, that I am trying to apply to the Lyft challenge. Very good explanation of the basics

\n

https://arxiv.org/pdf/2004.05214.pdf

", "votes": null, "replies": [] } ], "raw_markdown_by_id": { "984155": "* Deep Learning-based Vehicle Behaviour Prediction for Autonomous Driving Applications: [a Review](https://arxiv.org/pdf/1912.11676.pdf)", "984321": "Just found a list of papers from CVPR2019 related to Autonomous Driving. If you find any of them are useful, please add them to your list\n1、Pseudo-LiDAR from Visual Depth Estimation: Bridging the Gap in 3D Object Detection for Autonomous Driving\nhttps://arxiv.org/abs/1812.07179\nhttps://github.com/mileyan/pseudo_lidar\n2、ApolloCar3D: A Large 3D Car Instance Understanding Benchmark for Autonomous Driving\nhttps://arxiv.org/abs/1811.12222\n3、Group-wise Correlation Stereo Network\nhttps://arxiv.org/abs/1903.04025\n4、Stereo R-CNN based 3D Object Detection for Autonomous Driving\nhttps://arxiv.org/abs/1902.09738\n5、Deep Rigid Instance Scene Flow\nhttps://people.csail.mit.edu/weichium/papers/cvpr19-dsisf/paper.pdf\n6、An Efficient Schmidt-EKF for 3D visual-inertial SLAM\nhttps://arxiv.org/abs/1903.08636\n7、LaserNet: An Efficient Probabilistic 3D Object Detector for Autonomous Driving\nGregory P. Meyer, Ankit Laddha, Eric Kee, Carlos Vallespi-Gonzalez, Carl K. Wellington\nhttps://arxiv.org/abs/1903.08701\n8、.GS3D: An Efficient 3D Object Detection Framework for Autonomous Driving\nhttps://arxiv.org/abs/1903.10955\n9、Learning to Adapt for Stereo\nhttps://arxiv.org/abs/1904.02957\nhttps://github.com/CVLAB-Unibo/Learning2AdaptForStereo\n10、What Object Should I Use? - Task Driven Object Detection\nhttps://arxiv.org/abs/1904.03000\n11、YUVMultiNet: Real-time YUV multi-task CNN for autonomous driving\nhttps://arxiv.org/abs/1904.05673\n12、L3-Net: Towards Learning-based LiDAR Localization for Autonomous Driving\nhttps://songshiyu01.github.io/pdf/L3Net_W.Lu_Y.Zhou_S.Song_CVPR2019.pdf", "984447": "thanks for share", "984958": "Here are all the papers with code from the CVPR 2020:\nhttps://paperswithcode.com/conference/cvpr-2020-6", "985465": "If you're looking for SOTA on behavior prediction, there are some new papers coming out. Also, it can be overwhelming to read a long list of papers. The following papers I've seen to be picked as baselines for SOTA comparison,\n\nCovernet https://arxiv.org/pdf/1911.10298.pdf\nMultipath https://arxiv.org/pdf/1910.05449.pdf\nMTP https://arxiv.org/abs/1809.10732\nSpaGNN https://arxiv.org/pdf/1910.08233.pdf (this one is joint perception & prediction however, the idea around prediction can be reused)", "1002636": "I had a look also at a citing review that addresses the topic of video prediction, that I am trying to apply to the Lyft challenge. Very good explanation of the basics\n\n https://arxiv.org/pdf/2004.05214.pdf" }, "source": "meta" }