AI Research 技术调研

标签: multi-view

此标签下有7条笔记。

  • 2026年7月16日

    MV-UMI: A Scalable Multi-View Interface for Cross-Embodiment Learning

    • cross-embodiment
    • handheld-gripper
    • UMI
    • multi-view
    • teleoperation-free
    • SAM-2
    • inpainting
    • diffusion-policy
    • three-jaw-gripper
    • imitation-learning
  • 2026年7月16日

    Cosmos-Drive-Dreams: Scalable Synthetic Driving Data Generation with World Foundation Models

    • world-model
    • autonomous-driving
    • synthetic-data
    • controlnet
    • multi-view
    • lidar-generation
    • diffusion
    • dit
    • cosmos
    • data-flywheel
  • 2026年7月16日

    EnerVerse: Envisioning Embodied Future Space for Robotics Manipulation

    • world-model
    • video-diffusion
    • robotic-manipulation
    • multi-view
    • free-anchor-view
    • 4d-gaussian-splatting
    • sim2real
    • chunk-autoregressive
    • sparse-memory
    • libero
  • 2026年7月16日

    MultiWorld: Scalable Multi-Agent Multi-View Video World Models

    • world-model
    • multi-agent
    • multi-view
    • video-generation
    • flow-matching
    • action-conditioning
    • robotics-manipulation
    • embodied-ai
    • HKU
    • VGGT
    • RoPE
  • 2026年6月25日

    One-2-3-45: Any Single Image to 3D Mesh in 45 Seconds without Per-Shape Optimization

    • image-to-3d
    • single-image-reconstruction
    • zero123
    • sdf
    • sparseneus
    • feed-forward
    • neurips-2023
    • multi-view
  • 2026年6月25日

    Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasets

    • video
    • image-to-video
    • text-to-video
    • latent-diffusion
    • data-curation
    • open-source
    • edm
    • multi-view
    • Clips
  • 2026年6月25日

    Zero123++: a Single Image to Consistent Multi-view Diffusion Base Model

    • 3d
    • multi-view
    • novel-view-synthesis
    • diffusion
    • stable-diffusion
    • reference-attention
    • controlnet
    • objaverse

  • GitHub