Collaborative Score Distillation for Consistent Visual Synthesis

• URL: http://arxiv.org/abs/2307.04787v1
• Date: Tue, 4 Jul 2023 17:31:50 GMT
• Title: Collaborative Score Distillation for Consistent Visual Synthesis
• Authors: Subin Kim, Kyungmin Lee, June Suk Choi, Jongheon Jeong, Kihyuk Sohn, Jinwoo Shin
• Abstract summary: Collaborative Score Distillation (CSD) is based on the Stein Variational Gradient Descent (SVGD) We show the effectiveness of CSD in a variety of tasks, encompassing the visual editing of panorama images, videos, and 3D scenes. Our results underline the competency of CSD as a versatile method for enhancing inter-sample consistency, thereby broadening the applicability of text-to-image diffusion models.
• Score: 70.29294250371312
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Generative priors of large-scale text-to-image diffusion models enable a wide range of new generation and editing applications on diverse visual modalities. However, when adapting these priors to complex visual modalities, often represented as multiple images (e.g., video), achieving consistency across a set of images is challenging. In this paper, we address this challenge with a novel method, Collaborative Score Distillation (CSD). CSD is based on the Stein Variational Gradient Descent (SVGD). Specifically, we propose to consider multiple samples as "particles" in the SVGD update and combine their score functions to distill generative priors over a set of images synchronously. Thus, CSD facilitates seamless integration of information across 2D images, leading to a consistent visual synthesis across multiple samples. We show the effectiveness of CSD in a variety of tasks, encompassing the visual editing of panorama images, videos, and 3D scenes. Our results underline the competency of CSD as a versatile method for enhancing inter-sample consistency, thereby broadening the applicability of text-to-image diffusion models.

Related papers

• Semantic Score Distillation Sampling for Compositional Text-to-3D Generation [28.88237230872795]
  Generating high-quality 3D assets from textual descriptions remains a pivotal challenge in computer graphics and vision research. We introduce a novel SDS approach, designed to improve the expressiveness and accuracy of compositional text-to-3D generation. Our approach integrates new semantic embeddings that maintain consistency across different rendering views. By leveraging explicit semantic guidance, our method unlocks the compositional capabilities of existing pre-trained diffusion models.
  arXiv  Detail & Related papers  (2024-10-11T17:26:00Z)
• MultiDiff: Consistent Novel View Synthesis from a Single Image [60.04215655745264]
  MultiDiff is a novel approach for consistent novel view synthesis of scenes from a single RGB image. Our results demonstrate that MultiDiff outperforms state-of-the-art methods on the challenging, real-world datasets RealEstate10K and ScanNet.
  arXiv  Detail & Related papers  (2024-06-26T17:53:51Z)
• Grounded Compositional and Diverse Text-to-3D with Pretrained Multi-View Diffusion Model [65.58911408026748]
  We propose Grounded-Dreamer to generate 3D assets that can accurately follow complex, compositional text prompts. We first advocate leveraging text-guided 4-view images as the bottleneck in the text-to-3D pipeline. We then introduce an attention refocusing mechanism to encourage text-aligned 4-view image generation.
  arXiv  Detail & Related papers  (2024-04-28T04:05:10Z)
• Many-to-many Image Generation with Auto-regressive Diffusion Models [59.5041405824704]
  This paper introduces a domain-general framework for many-to-many image generation, capable of producing interrelated image series from a given set of images. We present MIS, a novel large-scale multi-image dataset, containing 12M synthetic multi-image samples, each with 25 interconnected images. We learn M2M, an autoregressive model for many-to-many generation, where each image is modeled within a diffusion framework.
  arXiv  Detail & Related papers  (2024-04-03T23:20:40Z)
• 3D-aware Image Generation and Editing with Multi-modal Conditions [6.444512435220748]
  3D-consistent image generation from a single 2D semantic label is an important and challenging research topic in computer graphics and computer vision. We propose a novel end-to-end 3D-aware image generation and editing model incorporating multiple types of conditional inputs. Our method can generate diverse images with distinct noises, edit the attribute through a text description and conduct style transfer by giving a reference RGB image.
  arXiv  Detail & Related papers  (2024-03-11T07:10:37Z)
• IT3D: Improved Text-to-3D Generation with Explicit View Synthesis [71.68595192524843]
  This study presents a novel strategy that leverages explicitly synthesized multi-view images to address these issues. Our approach involves the utilization of image-to-image pipelines, empowered by LDMs, to generate posed high-quality images. For the incorporated discriminator, the synthesized multi-view images are considered real data, while the renderings of the optimized 3D models function as fake data.
  arXiv  Detail & Related papers  (2023-08-22T14:39:17Z)
• Guide3D: Create 3D Avatars from Text and Image Guidance [55.71306021041785]
  Guide3D is a text-and-image-guided generative model for 3D avatar generation based on diffusion models. Our framework produces topologically and structurally correct geometry and high-resolution textures.
  arXiv  Detail & Related papers  (2023-08-18T17:55:47Z)
• Text-driven Visual Synthesis with Latent Diffusion Prior [37.736313030226654]
  We present a generic approach using latent diffusion models as powerful image priors for various visual synthesis tasks. We demonstrate the efficacy of our approach on three different applications, text-to-3D, StyleGAN adaptation, and layered image editing.
  arXiv  Detail & Related papers  (2023-02-16T18:59:58Z)

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.