How Far are AI-generated Videos from Simulating the 3D Visual World: A Learned 3D Evaluation Approach

Documenti analoghi

• Total-Decom: Decomposed 3D Scene Reconstruction with Minimal Interaction
  di: Lyu, Xiaoyang, et al.
  Pubblicazione: (2024)
• ASSIST-3D: Adapted Scene Synthesis for Class-Agnostic 3D Instance Segmentation
  di: Zhou, Shengchao, et al.
  Pubblicazione: (2025)
• ObjectMorpher: 3D-Aware Image Editing via Deformable 3DGS Models
  di: Xie, Yuhuan, et al.
  Pubblicazione: (2026)
• DO3D: Self-supervised Learning of Decomposed Object-aware 3D Motion and Depth from Monocular Videos
  di: Wu, Xiuzhe, et al.
  Pubblicazione: (2024)
• AniGen: Unified $S^3$ Fields for Animatable 3D Asset Generation
  di: Huang, Yi-Hua, et al.
  Pubblicazione: (2026)