• Home
  • Technology
  • Gaming
  • Entertainment
  • World & Business
  • Science
  • Sports
  • AI
HomeTechnologyGamingEntertainmentWorld & BusinessScienceSportsAI
  • HomeTechnologyGamingEntertainmentWorld & BusinessScienceSportsAI
    • Home
    • Technology
    • Gaming
    • Entertainment
    • World & Business
    • Science
    • Sports
    • AI
    AI
    Announcement

    Point2Part introduced for point-guided 3D shape decomposition

    A researcher behind Point2Part says users can mark the parts they want with 3D points, and the model divides the whole shape into complete, non-overlapping parts.

    KK
    HT
    2 Sources, ,

    TLDR

    A researcher introducing Point2Part says the model partitions a whole 3D shape rather than predicting each part independently. It uses points to specify desired parts and supports image-to-parts, mesh-to-parts and mesh segmentation. The researcher claims state-of-the-art part quality and more than 10-fold lower inter-part penetration.

    Combined views

    3.6K

    2 Sources, first seen 14h ago

    Combined views

    3.6K

    2 Sources, first seen 14h ago

    18 likes
    14h ago
    first seen 14h ago
    18 likes
    11 saves
    12 reposts

    Sentiment

    Positive——Negative

    Summary

    Not enough discussion yet.

    No sentiment analysis available yet.

    Featured Source
    11 saves
    12 reposts

    Sentiment

    Positive——Negative

    Summary

    Not enough discussion yet.

    No sentiment analysis available yet.

    Today's Rank

    —

    Not ranked yet

    Today's Rank

    —

    Not ranked yet

    2 Sources

    @henrytsui000❓ What should 3D part decomposition look like? 📣 Introducing Point2Part, a unified model that treats 3D part decomposition as a partition of the whole, rather than a collection of independently predicted parts. Point2Part lets users specify the parts they want with 3D points and produces a complete, non-overlapping decomposition of the whole shape. One model supports image→parts, mesh→parts, and mesh segmentation, achieving SOTA part quality with >10× lower inter-part penetration. 📄 arXiv: https://arxiv.org/abs/2609.38180 🌐 Project: https://henrytsui000.github.io/Point2Part/ Joint work with @LucyTuan1, @XiaoxuanMa_, @nicougrinovic, Takaaki Shiratori, and @kkitani.
    @kkitaniRT @henrytsui000: ❓ What should 3D part decomposition look like? 📣 Introducing Point2Part, a unified model that treats 3D part decomposit…

    2 Sources

    @henrytsui000❓ What should 3D part decomposition look like? 📣 Introducing Point2Part, a unified model that treats 3D part decomposition as a partition of the whole, rather than a collection of independently predicted parts. Point2Part lets users specify the parts they want with 3D points and produces a complete, non-overlapping decomposition of the whole shape. One model supports image→parts, mesh→parts, and mesh segmentation, achieving SOTA part quality with >10× lower inter-part penetration. 📄 arXiv: https://arxiv.org/abs/2609.38180 🌐 Project: https://henrytsui000.github.io/Point2Part/ Joint work with @LucyTuan1, @XiaoxuanMa_, @nicougrinovic, Takaaki Shiratori, and @kkitani.
    @kkitaniRT @henrytsui000: ❓ What should 3D part decomposition look like? 📣 Introducing Point2Part, a unified model that treats 3D part decomposit…