A self-supervised fine-tuned multi-view diffusion model produces six consistent de-occluded views from one occluded image, improving downstream 3D reconstruction over two-stage baselines.
Zero-1-to-3: Zero-shot one image to 3d object,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
DeOcc-1-to-3: 3D De-Occlusion from a Single Image via Self-Supervised Multi-View Diffusion
A self-supervised fine-tuned multi-view diffusion model produces six consistent de-occluded views from one occluded image, improving downstream 3D reconstruction over two-stage baselines.