Latent Bias Alignment for High-Fidelity Diffusion Inversion in Real-World Image Reconstruction and Manipulation
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2026
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866911543316185088 |
|---|---|
| author | Chen, Weiming Liu, Qifan Liu, Siyi Tang, Yushun Wang, Yijia Zhu, Zhihan He, Zhihai |
| author_facet | Chen, Weiming Liu, Qifan Liu, Siyi Tang, Yushun Wang, Yijia Zhu, Zhihan He, Zhihai |
| contents | Recent research has shown that text-to-image diffusion models are capable of generating high-quality images guided by text prompts. But can they be used to generate or approximate real-world images from the seed noise? This is known as the diffusion inversion problem, which serves as a fundamental building block for bridging diffusion models and real-world scenarios. However, existing diffusion inversion methods often suffer from low reconstruction quality or weak robustness. Two major challenges need to be carefully addressed: (1) the misalignment between the inversion and generation trajectories during the diffusion process, and (2) the mismatch between the diffusion inversion process and the VQ autoencoder (VQAE) reconstruction. To address these challenges, we introduce a latent bias vector at each inversion step, which is learned to reduce the misalignment between inversion and generation trajectories. We refer to this strategy as Latent Bias Optimization (LBO). Furthermore, we perform an approximate joint optimization of the diffusion inversion and VQAE reconstruction processes by learning to adjust the image latent representation, which serves as the connecting interface between them. We refer to this technique as Image Latent Boosting (ILB). Extensive experimental results demonstrate that the proposed method significantly improves the image reconstruction quality of the diffusion model, as well as the performance of downstream tasks, including image editing and rare concept generation. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_23903 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Latent Bias Alignment for High-Fidelity Diffusion Inversion in Real-World Image Reconstruction and Manipulation Chen, Weiming Liu, Qifan Liu, Siyi Tang, Yushun Wang, Yijia Zhu, Zhihan He, Zhihai Computer Vision and Pattern Recognition Artificial Intelligence Recent research has shown that text-to-image diffusion models are capable of generating high-quality images guided by text prompts. But can they be used to generate or approximate real-world images from the seed noise? This is known as the diffusion inversion problem, which serves as a fundamental building block for bridging diffusion models and real-world scenarios. However, existing diffusion inversion methods often suffer from low reconstruction quality or weak robustness. Two major challenges need to be carefully addressed: (1) the misalignment between the inversion and generation trajectories during the diffusion process, and (2) the mismatch between the diffusion inversion process and the VQ autoencoder (VQAE) reconstruction. To address these challenges, we introduce a latent bias vector at each inversion step, which is learned to reduce the misalignment between inversion and generation trajectories. We refer to this strategy as Latent Bias Optimization (LBO). Furthermore, we perform an approximate joint optimization of the diffusion inversion and VQAE reconstruction processes by learning to adjust the image latent representation, which serves as the connecting interface between them. We refer to this technique as Image Latent Boosting (ILB). Extensive experimental results demonstrate that the proposed method significantly improves the image reconstruction quality of the diffusion model, as well as the performance of downstream tasks, including image editing and rare concept generation. |
| title | Latent Bias Alignment for High-Fidelity Diffusion Inversion in Real-World Image Reconstruction and Manipulation |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2603.23903 |