Noise-Free Score Distillation

• URL: http://arxiv.org/abs/2310.17590v1
• Date: Thu, 26 Oct 2023 17:12:26 GMT
• Title: Noise-Free Score Distillation
• Authors: Oren Katzir, Or Patashnik, Daniel Cohen-Or, Dani Lischinski
• Abstract summary: Noise-Free Score Distillation (NFSD) process requires minimal modifications to the original SDS framework. We achieve more effective distillation of pre-trained text-to-image diffusion models while using a nominal CFG scale.
• Score: 78.79226724549456
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Score Distillation Sampling (SDS) has emerged as the de facto approach for text-to-content generation in non-image domains. In this paper, we reexamine the SDS process and introduce a straightforward interpretation that demystifies the necessity for large Classifier-Free Guidance (CFG) scales, rooted in the distillation of an undesired noise term. Building upon our interpretation, we propose a novel Noise-Free Score Distillation (NFSD) process, which requires minimal modifications to the original SDS framework. Through this streamlined design, we achieve more effective distillation of pre-trained text-to-image diffusion models while using a nominal CFG scale. This strategic choice allows us to prevent the over-smoothing of results, ensuring that the generated data is both realistic and complies with the desired prompt. To demonstrate the efficacy of NFSD, we provide qualitative examples that compare NFSD and SDS, as well as several other methods.

Related papers

• VividDreamer: Invariant Score Distillation For Hyper-Realistic Text-to-3D Generation [33.05759961083337]
  This paper presents Invariant Score Distillation (ISD), a novel method for high-fidelity text-to-3D generation. ISD aims to tackle the over-saturation and over-smoothing problems in Score Distillation Sampling (SDS)
  arXiv  Detail & Related papers  (2024-07-13T09:33:16Z)
• Flow Score Distillation for Diverse Text-to-3D Generation [23.38418695449777]
  Flow Score Distillation (FSD) substantially enhances generation diversity without compromising quality. Our validation experiments across various text-to-image Diffusion Models demonstrate that FSD substantially enhances generation diversity without compromising quality.
  arXiv  Detail & Related papers  (2024-05-16T06:05:16Z)
• Distilling Diffusion Models into Conditional GANs [90.76040478677609]
  We distill a complex multistep diffusion model into a single-step conditional GAN student model. For efficient regression loss, we propose E-LatentLPIPS, a perceptual loss operating directly in diffusion model's latent space. We demonstrate that our one-step generator outperforms cutting-edge one-step diffusion distillation models.
  arXiv  Detail & Related papers  (2024-05-09T17:59:40Z)
• A Quantitative Evaluation of Score Distillation Sampling Based Text-to-3D [54.78611187426158]
  We propose more objective quantitative evaluation metrics, which we cross-validate via human ratings, and show analysis of the failure cases of the SDS technique. We demonstrate the effectiveness of this analysis by designing a novel computationally efficient baseline model.
  arXiv  Detail & Related papers  (2024-02-29T00:54:09Z)
• Score Distillation Sampling with Learned Manifold Corrective [36.963929141091455]
  We decompose the loss into different factors and isolate the component responsible for noisy gradients. In the original formulation, high text guidance is used to account for the noise, leading to unwanted side effects such as oversaturation or repeated detail. We train a shallow network mimicking the timestep-dependent frequency bias of the image diffusion model in order to effectively factor it out.
  arXiv  Detail & Related papers  (2024-01-10T17:51:46Z)
• Adversarial Score Distillation: When score distillation meets GAN [3.2794321281011394]
  We decipher existing score distillation with the Wasserstein Generative Adversarial Network (WGAN) paradigm. With the WGAN paradigm, we find that existing score distillation either employs a fixed sub-optimal discriminator or conducts incomplete discriminator optimization. We propose the Adversarial Score Distillation (ASD), which maintains an optimizable discriminator and updates it using the complete optimization objective.
  arXiv  Detail & Related papers  (2023-12-01T17:20:47Z)
• Contrastive Denoising Score for Text-guided Latent Diffusion Image Editing [58.48890547818074]
  We present a powerful modification of Contrastive Denoising Score (CUT) for latent diffusion models (LDM) Our approach enables zero-shot imageto-image translation and neural field (NeRF) editing, achieving structural correspondence between the input and output.
  arXiv  Detail & Related papers  (2023-11-30T15:06:10Z)
• SAR Despeckling using a Denoising Diffusion Probabilistic Model [52.25981472415249]
  The presence of speckle degrades the image quality and adversely affects the performance of SAR image understanding applications. We introduce SAR-DDPM, a denoising diffusion probabilistic model for SAR despeckling. The proposed method achieves significant improvements in both quantitative and qualitative results over the state-of-the-art despeckling methods.
  arXiv  Detail & Related papers  (2022-06-09T14:00:26Z)
• Salvage Reusable Samples from Noisy Data for Robust Learning [70.48919625304]
  We propose a reusable sample selection and correction approach, termed as CRSSC, for coping with label noise in training deep FG models with web images. Our key idea is to additionally identify and correct reusable samples, and then leverage them together with clean examples to update the networks.
  arXiv  Detail & Related papers  (2020-08-06T02:07:21Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.