Alapfogalmak
Proposing O2-Recon framework for accurate and complete 3D reconstruction of occluded objects using a pre-trained 2D diffusion model.
Statisztikák
Experiments on ScanNet scenes show that our proposed framework achieves state-of-the-art accuracy and completeness in object-level reconstruction from scene-level RGB-D videos.
Idézetek
"Occlusion is a common issue in 3D reconstruction from RGB-D videos, often blocking the complete reconstruction of objects."
"We propose a novel framework empowered by a 2D diffusion-based in-painting model to reconstruct complete surfaces for the hidden parts of objects."