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

    Nvidia introduces Axolotl3D for 3D reconstruction

    Nvidia says the model combines images, camera data and partial geometry to reconstruct missing regions of objects while preserving the parts already observed.

    NA
    1 Source, 14d ago, first seen 14d ago

    TLDR

    Nvidia introduced Axolotl3D at ECCV 2026, describing it as a 3D generation model that accounts for hidden parts of objects. The company says it uses images, camera data and partial geometry to reconstruct missing regions while preserving observed ones, and claims state-of-the-art results across single- and multi-view settings.

    Combined views

    26.2K

    1 Source, first seen 14d ago

    Combined views

    26.2K

    1 Source, first seen 14d ago

    447 likes
    447 likes
    20 comments
    230 saves
    52 reposts

    Sentiment

    Positive——Negative

    Summary

    Not enough discussion yet.

    No sentiment analysis available yet.

    20 comments
    230 saves
    52 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

    1 Source

    @NVIDIAAIImages rarely show an object’s full 3D geometry. At #ECCV2026, our research team introduced Axolotl3D, a multimodal and occlusion-aware 3D generation model. It combines images, camera data and partial geometry to reconstruct missing regions while preserving observed ones, achieving state-of-the-art results across single- and multi-view settings. Project page: https://research.nvidia.com/labs/sil/projects/axolotl3d

    1 Source

    @NVIDIAAIImages rarely show an object’s full 3D geometry. At #ECCV2026, our research team introduced Axolotl3D, a multimodal and occlusion-aware 3D generation model. It combines images, camera data and partial geometry to reconstruct missing regions while preserving observed ones, achieving state-of-the-art results across single- and multi-view settings. Project page: https://research.nvidia.com/labs/sil/projects/axolotl3d