Identity-preserving Distillation Sampling by Fixed-Point Iterator
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866908282785890304 |
|---|---|
| author | Kim, SeonHwa Kim, Jiwon Park, Soobin Ahn, Donghoon Kang, Jiwon Kim, Seungryong Jin, Kyong Hwan Cha, Eunju |
| author_facet | Kim, SeonHwa Kim, Jiwon Park, Soobin Ahn, Donghoon Kang, Jiwon Kim, Seungryong Jin, Kyong Hwan Cha, Eunju |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_19930 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Identity-preserving Distillation Sampling by Fixed-Point Iterator Kim, SeonHwa Kim, Jiwon Park, Soobin Ahn, Donghoon Kang, Jiwon Kim, Seungryong Jin, Kyong Hwan Cha, Eunju Computer Vision and Pattern Recognition 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. |
| title | Identity-preserving Distillation Sampling by Fixed-Point Iterator |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2502.19930 |