Identity-preserving Distillation Sampling by Fixed-Point Iterator
This addresses identity preservation in image-to-image and NeRF editing for generative AI applications, representing an incremental improvement over existing de-biasing techniques.
The paper tackled the problem of blurriness and identity loss in score distillation sampling (SDS) for text-conditioned image and 3D object generation by introducing Identity-preserving Distillation Sampling (IDS) with fixed-point iterative regularization (FPR), resulting in clear representations and maintained structural consistency in editing tasks.
Score distillation sampling (SDS) demonstrates a powerful capability for text-conditioned 2D image and 3D object generation by distilling the knowledge from learned score functions. However, SDS often suffers from blurriness caused by noisy gradients. When SDS meets the image editing, such degradations can be reduced by adjusting bias shifts using reference pairs, but the de-biasing techniques are still corrupted by erroneous gradients. To this end, we introduce Identity-preserving Distillation Sampling (IDS), which compensates for the gradient leading to undesired changes in the results. Based on the analysis that these errors come from the text-conditioned scores, a new regularization technique, called fixed-point iterative regularization (FPR), is proposed to modify the score itself, driving the preservation of the identity even including poses and structures. Thanks to a self-correction by FPR, the proposed method provides clear and unambiguous representations corresponding to the given prompts in image-to-image editing and editable neural radiance field (NeRF). The structural consistency between the source and the edited data is obviously maintained compared to other state-of-the-art methods.