Preserving Identity with Variational Score for General-purpose 3D Editing

• URL: http://arxiv.org/abs/2406.08953v1
• Date: Thu, 13 Jun 2024 09:32:40 GMT
• Title: Preserving Identity with Variational Score for General-purpose 3D Editing
• Authors: Duong H. Le, Tuan Pham, Aniruddha Kembhavi, Stephan Mandt, Wei-Chiu Ma, Jiasen Lu,
• Abstract summary: Piva is a novel optimization-based method for editing images and 3D models based on diffusion models. We pinpoint the limitations in 2D and 3D editing, which causes detail loss and oversaturation. We propose an additional score distillation term that enforces identity preservation.
• Score: 48.314327790451856
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We present Piva (Preserving Identity with Variational Score Distillation), a novel optimization-based method for editing images and 3D models based on diffusion models. Specifically, our approach is inspired by the recently proposed method for 2D image editing - Delta Denoising Score (DDS). We pinpoint the limitations in DDS for 2D and 3D editing, which causes detail loss and over-saturation. To address this, we propose an additional score distillation term that enforces identity preservation. This results in a more stable editing process, gradually optimizing NeRF models to match target prompts while retaining crucial input characteristics. We demonstrate the effectiveness of our approach in zero-shot image and neural field editing. Our method successfully alters visual attributes, adds both subtle and substantial structural elements, translates shapes, and achieves competitive results on standard 2D and 3D editing benchmarks. Additionally, our method imposes no constraints like masking or pre-training, making it compatible with a wide range of pre-trained diffusion models. This allows for versatile editing without needing neural field-to-mesh conversion, offering a more user-friendly experience.

Related papers

• Stable Flow: Vital Layers for Training-Free Image Editing [74.52248787189302]
  Diffusion models have revolutionized the field of content synthesis and editing. Recent models have replaced the traditional UNet architecture with the Diffusion Transformer (DiT) We propose an automatic method to identify "vital layers" within DiT, crucial for image formation. Next, to enable real-image editing, we introduce an improved image inversion method for flow models.
  arXiv  Detail & Related papers  (2024-11-21T18:59:51Z)
• 3D Gaussian Editing with A Single Image [19.662680524312027]
  We introduce a novel single-image-driven 3D scene editing approach based on 3D Gaussian Splatting. Our method learns to optimize the 3D Gaussians to align with an edited version of the image rendered from a user-specified viewpoint. Experiments show the effectiveness of our method in handling geometric details, long-range, and non-rigid deformation.
  arXiv  Detail & Related papers  (2024-08-14T13:17:42Z)
• DreamCatalyst: Fast and High-Quality 3D Editing via Controlling Editability and Identity Preservation [17.930032337081673]
  Score distillation sampling (SDS) has emerged as an effective framework in text-driven 3D editing tasks. We propose DreamCatalyst, a novel framework that considers these sampling dynamics in the SDS framework. Our method offers two modes: (1) a fast mode that edits scenes 23 times faster than current state-of-the-art NeRF editing methods, and (2) a high-quality mode that produces superior results about 8 times faster than these methods.
  arXiv  Detail & Related papers  (2024-07-16T05:26:14Z)
• DGE: Direct Gaussian 3D Editing by Consistent Multi-view Editing [72.54566271694654]
  We consider the problem of editing 3D objects and scenes based on open-ended language instructions. A common approach to this problem is to use a 2D image generator or editor to guide the 3D editing process. This process is often inefficient due to the need for iterative updates of costly 3D representations.
  arXiv  Detail & Related papers  (2024-04-29T17:59:30Z)
• 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)
• ED-NeRF: Efficient Text-Guided Editing of 3D Scene with Latent Space NeRF [60.47731445033151]
  We present a novel 3D NeRF editing approach dubbed ED-NeRF. We embed real-world scenes into the latent space of the latent diffusion model (LDM) through a unique refinement layer. This approach enables us to obtain a NeRF backbone that is not only faster but also more amenable to editing.
  arXiv  Detail & Related papers  (2023-10-04T10:28:38Z)
• Editing 3D Scenes via Text Prompts without Retraining [80.57814031701744]
  DN2N is a text-driven editing method that allows for the direct acquisition of a NeRF model with universal editing capabilities. Our method employs off-the-shelf text-based editing models of 2D images to modify the 3D scene images. Our method achieves multiple editing types, including but not limited to appearance editing, weather transition, material changing, and style transfer.
  arXiv  Detail & Related papers  (2023-09-10T02:31:50Z)
• In-N-Out: Faithful 3D GAN Inversion with Volumetric Decomposition for Face Editing [28.790900756506833]
  3D-aware GANs offer new capabilities for view synthesis while preserving the editing functionalities of their 2D counterparts. GAN inversion is a crucial step that seeks the latent code to reconstruct input images or videos, subsequently enabling diverse editing tasks through manipulation of this latent code. We address this issue by explicitly modeling OOD objects from the input in 3D-aware GANs.
  arXiv  Detail & Related papers  (2023-02-09T18:59:56Z)

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.