home.social

#3dv2024 — Public Fediverse posts

Live and recent posts from across the Fediverse tagged #3dv2024, aggregated by home.social.

  1. If you missed our demo at #3DV2024 , our setup will be presented at the #ICRA mobile manipulation workshop and we just finished to cut it into a nice video:

    Spot-Compose: A Framework for Open-Vocabulary Object Retrieval and Drawer Manipulation in Point Clouds
    📄 Paper: arxiv.org/abs/2404.12440
    🔗 Webpage: spot-compose.github.io/
    📹 Video: youtu.be/4BRKIzyaT3o?si=XB9SF4

    #robotics #BostonDynamcis #spot #eth_zurich @cvg #computervision

  2. If you missed our demo at #3DV2024 , our setup will be presented at the #ICRA mobile manipulation workshop and we just finished to cut it into a nice video:

    Spot-Compose: A Framework for Open-Vocabulary Object Retrieval and Drawer Manipulation in Point Clouds
    📄 Paper: arxiv.org/abs/2404.12440
    🔗 Webpage: spot-compose.github.io/
    📹 Video: youtu.be/4BRKIzyaT3o?si=XB9SF4

    #robotics #BostonDynamcis #spot #eth_zurich @cvg #computervision

  3. If you missed our demo at #3DV2024 , our setup will be presented at the #ICRA mobile manipulation workshop and we just finished to cut it into a nice video:

    Spot-Compose: A Framework for Open-Vocabulary Object Retrieval and Drawer Manipulation in Point Clouds
    📄 Paper: arxiv.org/abs/2404.12440
    🔗 Webpage: spot-compose.github.io/
    📹 Video: youtu.be/4BRKIzyaT3o?si=XB9SF4

    #robotics #BostonDynamcis #spot #eth_zurich @cvg #computervision

  4. If you missed our demo at #3DV2024 , our setup will be presented at the #ICRA mobile manipulation workshop and we just finished to cut it into a nice video:

    Spot-Compose: A Framework for Open-Vocabulary Object Retrieval and Drawer Manipulation in Point Clouds
    📄 Paper: arxiv.org/abs/2404.12440
    🔗 Webpage: spot-compose.github.io/
    📹 Video: youtu.be/4BRKIzyaT3o?si=XB9SF4

    #robotics #BostonDynamcis #spot #eth_zurich @cvg #computervision

  5. Today we release the code for LabelMaker, a tool to automatically create semantic annotation for indoor scenes. We produce labels in 2D and 3D by lifting an ensemble of SOTA models in a common label space. LabelMaker will be presented as spotlight at #3DV2024 in March.

    🔗 labelmaker.org
    🛠️ github.com/cvg/LabelMaker
    📄 arxiv.org/abs/2311.12174

    #computervision #robotics #3DV