SINE: Semantic-driven Image-based NeRF Editing with Prior-guided Editing
Field
- URL: http://arxiv.org/abs/2303.13277v2
- Date: Sat, 25 Mar 2023 14:58:22 GMT
- Title: SINE: Semantic-driven Image-based NeRF Editing with Prior-guided Editing
Field
- Authors: Chong Bao, Yinda Zhang, Bangbang Yang, Tianxing Fan, Zesong Yang,
Hujun Bao, Guofeng Zhang and Zhaopeng Cui
- Abstract summary: We present a novel semantic-driven NeRF editing approach, which enables users to edit a neural radiance field with a single image.
To achieve this goal, we propose a prior-guided editing field to encode fine-grained geometric and texture editing in 3D space.
Our method achieves photo-realistic 3D editing using only a single edited image, pushing the bound of semantic-driven editing in 3D real-world scenes.
- Score: 37.8162035179377
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Despite the great success in 2D editing using user-friendly tools, such as
Photoshop, semantic strokes, or even text prompts, similar capabilities in 3D
areas are still limited, either relying on 3D modeling skills or allowing
editing within only a few categories. In this paper, we present a novel
semantic-driven NeRF editing approach, which enables users to edit a neural
radiance field with a single image, and faithfully delivers edited novel views
with high fidelity and multi-view consistency. To achieve this goal, we propose
a prior-guided editing field to encode fine-grained geometric and texture
editing in 3D space, and develop a series of techniques to aid the editing
process, including cyclic constraints with a proxy mesh to facilitate geometric
supervision, a color compositing mechanism to stabilize semantic-driven texture
editing, and a feature-cluster-based regularization to preserve the irrelevant
content unchanged. Extensive experiments and editing examples on both
real-world and synthetic data demonstrate that our method achieves
photo-realistic 3D editing using only a single edited image, pushing the bound
of semantic-driven editing in 3D real-world scenes. Our project webpage:
https://zju3dv.github.io/sine/.
Related papers
- PrEditor3D: Fast and Precise 3D Shape Editing [100.09112677669376]
We propose a training-free approach to 3D editing that enables the editing of a single shape within a few minutes.
The edited 3D mesh aligns well with the prompts, and remains identical for regions that are not intended to be altered.
arXiv Detail & Related papers (2024-12-09T15:44:47Z) - CTRL-D: Controllable Dynamic 3D Scene Editing with Personalized 2D Diffusion [13.744253074367885]
We introduce a novel framework that first fine-tunes the InstructPix2Pix model, followed by a two-stage optimization of the scene.
Our approach enables consistent and precise local edits without the need for tracking desired editing regions.
Compared to state-of-the-art methods, our approach offers more flexible and controllable local scene editing.
arXiv Detail & Related papers (2024-12-02T18:38:51Z) - ICE-G: Image Conditional Editing of 3D Gaussian Splats [45.112689255145625]
We introduce a novel approach to quickly edit a 3D model from a single reference view.
Our technique first segments the edit image, and then matches semantically corresponding regions across chosen segmented dataset views.
A color or texture change from a particular region of the edit image can then be applied to other views automatically in a semantically sensible manner.
arXiv Detail & Related papers (2024-06-12T17:59:52Z) - DATENeRF: Depth-Aware Text-based Editing of NeRFs [49.08848777124736]
We introduce an inpainting approach that leverages the depth information of NeRF scenes to distribute 2D edits across different images.
Our results reveal that this methodology achieves more consistent, lifelike, and detailed edits than existing leading methods for text-driven NeRF scene editing.
arXiv Detail & Related papers (2024-04-06T06:48:16Z) - Reference-Based 3D-Aware Image Editing with Triplanes [15.222454412573455]
Generative Adversarial Networks (GANs) have emerged as powerful tools for high-quality image generation and real image editing by manipulating their latent spaces.
Recent advancements in GANs include 3D-aware models such as EG3D, which feature efficient triplane-based architectures capable of reconstructing 3D geometry from single images.
This study addresses this gap by exploring and demonstrating the effectiveness of the triplane space for advanced reference-based edits.
arXiv Detail & Related papers (2024-04-04T17:53:33Z) - Real-time 3D-aware Portrait Editing from a Single Image [111.27169315556444]
3DPE can edit a face image following given prompts, like reference images or text descriptions.
A lightweight module is distilled from a 3D portrait generator and a text-to-image model.
arXiv Detail & Related papers (2024-02-21T18:36:26Z) - Plasticine3D: 3D Non-Rigid Editing with Text Guidance by Multi-View Embedding Optimization [21.8454418337306]
We propose Plasticine3D, a novel text-guided controlled 3D editing pipeline that can perform 3D non-rigid editing.
Our work divides the editing process into a geometry editing stage and a texture editing stage to achieve separate control of structure and appearance.
For the purpose of fine-grained control, we propose Embedding-Fusion (EF) to blend the original characteristics with the editing objectives in the embedding space.
arXiv Detail & Related papers (2023-12-15T09:01:54Z) - Learning Naturally Aggregated Appearance for Efficient 3D Editing [90.57414218888536]
We learn the color field as an explicit 2D appearance aggregation, also called canonical image.
We complement the canonical image with a projection field that maps 3D points onto 2D pixels for texture query.
Our approach demonstrates remarkable efficiency by being at least 20 times faster per edit compared to existing NeRF-based editing methods.
arXiv Detail & Related papers (2023-12-11T18:59:31Z) - Customize your NeRF: Adaptive Source Driven 3D Scene Editing via
Local-Global Iterative Training [61.984277261016146]
We propose a CustomNeRF model that unifies a text description or a reference image as the editing prompt.
To tackle the first challenge, we propose a Local-Global Iterative Editing (LGIE) training scheme that alternates between foreground region editing and full-image editing.
For the second challenge, we also design a class-guided regularization that exploits class priors within the generation model to alleviate the inconsistency problem.
arXiv Detail & Related papers (2023-12-04T06:25:06Z) - 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)
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.