DreamVVT: Mastering Realistic Video Virtual Try-On in the Wild via a Stage-Wise Diffusion Transformer Framework

Documenti analoghi

• TripVVT: A Large-Scale Triplet Dataset and a Coarse-Mask Baseline for In-the-Wild Video Virtual Try-On
  di: Shao, Dingbao, et al.
  Pubblicazione: (2026)
• RealVVT: Towards Photorealistic Video Virtual Try-on via Spatio-Temporal Consistency
  di: Li, Siqi, et al.
  Pubblicazione: (2025)
• 1-2-1: Renaissance of Single-Network Paradigm for Virtual Try-On
  di: Ning, Shuliang, et al.
  Pubblicazione: (2025)
• VITON-DiT: Learning In-the-Wild Video Try-On from Human Dance Videos via Diffusion Transformers
  di: Zheng, Jun, et al.
  Pubblicazione: (2024)
• DreamActor-H1: High-Fidelity Human-Product Demonstration Video Generation via Motion-designed Diffusion Transformers
  di: Wang, Lizhen, et al.
  Pubblicazione: (2025)