類似資料

• PF3plat: Pose-Free Feed-Forward 3D Gaussian Splatting
  著者:: Hong, Sunghwan, 等
  出版事項: (2024)
• Cross-View Completion Models are Zero-shot Correspondence Estimators
  著者:: An, Honggyu, 等
  出版事項: (2024)
• DirecT2V: Large Language Models are Frame-Level Directors for Zero-Shot Text-to-Video Generation
  著者:: Hong, Susung, 等
  出版事項: (2023)
• NoPe-NeRF++: Local-to-Global Optimization of NeRF with No Pose Prior
  著者:: Shi, Dongbo, 等
  出版事項: (2025)
• Entropy-Gradient Grounding: Training-Free Evidence Retrieval in Vision-Language Models
  著者:: Gröpl, Marcel, 等
  出版事項: (2026)