Ctrl123: Consistent Novel View Synthesis via Closed-Loop Transcription

Understand

Large image diffusion models have demonstrated zero-shot capability in novel view synthesis (NVS).

• However, existing diffusion-based NVS methods struggle to generate novel views that are accurately consistent with the corresponding ground truth poses and appearances, even on the training set.
• This consequently limits the performance of downstream tasks, such as image-to-multiview generation and 3D reconstruction.
• We realize that such inconsistency is largely due to the fact that it is difficult to enforce accurate pose and appearance alignment directly in the diffusion training, as mostly done by existing methods such as Zero123.