3D再構成
NeRF
text23D
3Dモデル生成
3D-LLM
Gaussian Splatting
空間表現
コンピューターグラフィクス(CG)
NVIDIA Research が、AI により 2D の写真を瞬時に 3D シーンに変換
https://blogs.nvidia.co.jp/blog/instant-nerf-research-3d-ai/
Crowning Achievement: NVIDIA Research Model Enables Fast, Efficient Dynamic Scene Reconstruction
https://blogs.nvidia.com/blog/neurips-2024-research/
PanoDreamer: 3D Panorama Synthesis from a Single Image
https://arxiv.org/abs/2412.04827
最近のSfM手法まとめ - COLMAP / GLOMAPを中心に -
https://speakerdeck.com/kwchrk/zui-jin-nosfmshou-fa-matome
PartGen: Part-level 3D Generation and Reconstruction with Multi-View Diffusion Models
https://arxiv.org/abs/2412.18608
SPAR3D: Stable Point-Aware Reconstruction of 3D Objects from Single Images
https://github.com/Stability-AI/stable-point-aware-3d
https://stability.ai/news/stable-point-aware-3d
Introducing Stable Virtual Camera: Multi-View Video Generation with 3D Camera Control
https://stability.ai/news/introducing-stable-virtual-camera-multi-view-video-generation-with-3d-camera-control