Diffusion Knows Transparency: Repurposing Video Diffusion for Transparent Object Depth and Normal Estimation

Documenti analoghi

• One View, Many Worlds: Single-Image to 3D Object Meets Generative Domain Randomization for One-Shot 6D Pose Estimation
  di: Geng, Zheng, et al.
  Pubblicazione: (2025)
• TransNormal: Dense Visual Semantics for Diffusion-based Transparent Object Normal Estimation
  di: Li, Mingwei, et al.
  Pubblicazione: (2026)
• Diffusion-Based Depth Inpainting for Transparent and Reflective Objects
  di: Sun, Tianyu, et al.
  Pubblicazione: (2024)
• Light-X: Generative 4D Video Rendering with Camera and Illumination Control
  di: Liu, Tianqi, et al.
  Pubblicazione: (2025)
• Monocular Depth Estimation and Segmentation for Transparent Object with Iterative Semantic and Geometric Fusion
  di: Liu, Jiangyuan, et al.
  Pubblicazione: (2025)