SERF: Fine-Grained Interactive 3D Segmentation and Editing with Radiance Fields

• URL: http://arxiv.org/abs/2312.15856v2
• Date: Thu, 31 Oct 2024 14:48:23 GMT
• Title: SERF: Fine-Grained Interactive 3D Segmentation and Editing with Radiance Fields
• Authors: Kaichen Zhou, Lanqing Hong, Enze Xie, Yongxin Yang, Zhenguo Li, Wei Zhang,
• Abstract summary: We introduce a novel fine-grained interactive 3D segmentation and editing algorithm with radiance fields, which we refer to as SERF. Our method entails creating a neural mesh representation by integrating multi-view algorithms with pre-trained 2D models. Building upon this representation, we introduce a novel surface rendering technique that preserves local information and is robust to deformation.
• Score: 92.14328581392633
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Although significant progress has been made in the field of 2D-based interactive editing, fine-grained 3D-based interactive editing remains relatively unexplored. This limitation can be attributed to two main challenges: the lack of an efficient 3D representation robust to different modifications and the absence of an effective 3D interactive segmentation method. In this paper, we introduce a novel fine-grained interactive 3D segmentation and editing algorithm with radiance fields, which we refer to as SERF. Our method entails creating a neural mesh representation by integrating multi-view algorithms with pre-trained 2D models. Building upon this representation, we introduce a novel surface rendering technique that preserves local information and is robust to deformation. Moreover, this representation forms the basis for achieving accurate and interactive 3D segmentation without requiring 3D supervision. Harnessing this representation facilitates a range of interactive 3D editing operations, encompassing tasks such as interactive geometry editing and texture painting. Extensive experiments and visualization examples of editing on both real and synthetic data demonstrate the superiority of our method on representation quality and editing ability.

Related papers

• REdiSplats: Ray Tracing for Editable Gaussian Splatting [0.0]
  We introduce REdiSplats, which employs ray tracing and a mesh-based representation of flat 3D Gaussians. In practice, we model the scene using flat Gaussian distributions parameterized by the mesh. We can render our models using 3D tools such as Blender or Nvdiffrast, which opens the possibility of integrating them with all existing 3D graphics techniques.
  arXiv  Detail & Related papers  (2025-03-15T22:42:21Z)
• MeshPad: Interactive Sketch-Conditioned Artist-Designed Mesh Generation and Editing [64.84885028248395]
  MeshPad is a generative approach that creates 3D meshes from sketch inputs. We focus on enabling consistent edits by decomposing editing into 'deletion' of regions of a mesh, followed by 'addition' of new mesh geometry. Our approach is based on a triangle sequence-based mesh representation, exploiting a large Transformer model for mesh triangle addition and deletion.
  arXiv  Detail & Related papers  (2025-03-03T11:27:44Z)
• MeshGS: Adaptive Mesh-Aligned Gaussian Splatting for High-Quality Rendering [61.64903786502728]
  We propose a novel approach that integrates mesh representation with 3D Gaussian splats to perform high-quality rendering of reconstructed real-world scenes. We consider the distance between each Gaussian splat and the mesh surface to distinguish between tightly-bound and loosely-bound splats. Our method surpasses recent mesh-based neural rendering techniques by achieving a 2dB higher PSNR, and outperforms mesh-based Gaussian splatting methods by 1.3 dB PSNR.
  arXiv  Detail & Related papers  (2024-10-11T16:07:59Z)
• HiSplat: Hierarchical 3D Gaussian Splatting for Generalizable Sparse-View Reconstruction [46.269350101349715]
  HiSplat is a novel framework for generalizable 3D Gaussian Splatting. It generates hierarchical 3D Gaussians via a coarse-to-fine strategy. It significantly enhances reconstruction quality and cross-dataset generalization.
  arXiv  Detail & Related papers  (2024-10-08T17:59:32Z)
• Towards Realistic Example-based Modeling via 3D Gaussian Stitching [31.710954782769377]
  We present an example-based modeling method that combines multiple Gaussian fields in a point-based representation using sample-guided synthesis. Specifically, as for composition, we create a GUI to segment and transform multiple fields in real time, easily obtaining a semantically meaningful composition of models. For texture blending, due to the discrete and irregular nature of 3DGS, straightforwardly applying gradient propagation as SeamlssNeRF is not supported.
  arXiv  Detail & Related papers  (2024-08-28T11:13:27Z)
• Chat-Edit-3D: Interactive 3D Scene Editing via Text Prompts [76.73043724587679]
  We propose a dialogue-based 3D scene editing approach, termed CE3D. Hash-Atlas represents 3D scene views, which transfers the editing of 3D scenes onto 2D atlas images. Results demonstrate that CE3D effectively integrates multiple visual models to achieve diverse editing visual effects.
  arXiv  Detail & Related papers  (2024-07-09T13:24:42Z)
• DragGaussian: Enabling Drag-style Manipulation on 3D Gaussian Representation [57.406031264184584]
  DragGaussian is a 3D object drag-editing framework based on 3D Gaussian Splatting. Our contributions include the introduction of a new task, the development of DragGaussian for interactive point-based 3D editing, and comprehensive validation of its effectiveness through qualitative and quantitative experiments.
  arXiv  Detail & Related papers  (2024-05-09T14:34:05Z)
• 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)
• SAGD: Boundary-Enhanced Segment Anything in 3D Gaussian via Gaussian Decomposition [66.56357905500512]
  3D Gaussian Splatting has emerged as an alternative 3D representation for novel view synthesis. We propose SAGD, a conceptually simple yet effective boundary-enhanced segmentation pipeline for 3D-GS. Our approach achieves high-quality 3D segmentation without rough boundary issues, which can be easily applied to other scene editing tasks.
  arXiv  Detail & Related papers  (2024-01-31T14:19:03Z)
• Learning Naturally Aggregated Appearance for Efficient 3D Editing [94.47518916521065]
  We propose to replace the color field with an explicit 2D appearance aggregation, also called canonical image. To avoid the distortion effect and facilitate convenient editing, we complement the canonical image with a projection field that maps 3D points onto 2D pixels for texture lookup. Our representation, dubbed AGAP, well supports various ways of 3D editing (e.g., stylization, interactive drawing, and content extraction) with no need of re-optimization.
  arXiv  Detail & Related papers  (2023-12-11T18:59:31Z)
• Gaussian Grouping: Segment and Edit Anything in 3D Scenes [65.49196142146292]
  We propose Gaussian Grouping, which extends Gaussian Splatting to jointly reconstruct and segment anything in open-world 3D scenes. Compared to the implicit NeRF representation, we show that the grouped 3D Gaussians can reconstruct, segment and edit anything in 3D with high visual quality, fine granularity and efficiency.
  arXiv  Detail & Related papers  (2023-12-01T17:09:31Z)
• GaussianEditor: Swift and Controllable 3D Editing with Gaussian Splatting [66.08674785436612]
  3D editing plays a crucial role in many areas such as gaming and virtual reality. Traditional 3D editing methods, which rely on representations like meshes and point clouds, often fall short in realistically depicting complex scenes. Our paper presents GaussianEditor, an innovative and efficient 3D editing algorithm based on Gaussian Splatting (GS), a novel 3D representation.
  arXiv  Detail & Related papers  (2023-11-24T14:46:59Z)
• Scene-Generalizable Interactive Segmentation of Radiance Fields [64.37093918762]
  We make the first attempt at Scene-Generalizable Interactive in Radiance Fields (SGISRF) We propose a novel SGISRF method, which can perform 3D object segmentation for novel (unseen) scenes represented by radiance fields, guided by only a few interactive user clicks in a given set of multi-view 2D images. Experiments on two real-world challenging benchmarks covering diverse scenes demonstrate 1) effectiveness and scene-generalizability of the proposed method, 2) favorable performance compared to classical method requiring scene-specific optimization.
  arXiv  Detail & Related papers  (2023-08-09T17:55:50Z)
• 3Deformer: A Common Framework for Image-Guided Mesh Deformation [27.732389685912214]
  Given a source 3D mesh with semantic materials, and a user-specified semantic image, 3Deformer can accurately edit the source mesh. Our 3Deformer is able to produce impressive results and reaches the state-of-the-art level.
  arXiv  Detail & Related papers  (2023-07-19T10:44:44Z)
• Vox-E: Text-guided Voxel Editing of 3D Objects [14.88446525549421]
  Large scale text-guided diffusion models have garnered significant attention due to their ability to synthesize diverse images. We present a technique that harnesses the power of latent diffusion models for editing existing 3D objects.
  arXiv  Detail & Related papers  (2023-03-21T17:36:36Z)
• 3D Neural Sculpting (3DNS): Editing Neural Signed Distance Functions [34.39282814876276]
  In this work, we propose the first method for efficient interactive editing of signed distance functions expressed through neural networks. Inspired by 3D sculpting software for meshes, we use a brush-based framework that is intuitive and can in the future be used by sculptors and digital artists.
  arXiv  Detail & Related papers  (2022-09-28T10:05:16Z)
• MvDeCor: Multi-view Dense Correspondence Learning for Fine-grained 3D Segmentation [91.6658845016214]
  We propose to utilize self-supervised techniques in the 2D domain for fine-grained 3D shape segmentation tasks. We render a 3D shape from multiple views, and set up a dense correspondence learning task within the contrastive learning framework. As a result, the learned 2D representations are view-invariant and geometrically consistent.
  arXiv  Detail & Related papers  (2022-08-18T00:48:15Z)

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.