PartGS:Learning Part-aware 3D Representations by Fusing 2D Gaussians and Superquadrics
- URL: http://arxiv.org/abs/2408.10789v2
- Date: Mon, 02 Dec 2024 17:04:07 GMT
- Title: PartGS:Learning Part-aware 3D Representations by Fusing 2D Gaussians and Superquadrics
- Authors: Zhirui Gao, Renjiao Yi, Yuhang Huang, Wei Chen, Chenyang Zhu, Kai Xu,
- Abstract summary: Low-level 3D representations, such as point clouds, meshes, NeRFs, and 3D Gaussians, are commonly used to represent 3D objects or scenes.
We introduce $textbfPartGS$, $textbfPart$-aware 3D reconstruction by a hybrid representation of 2D $textbfG$aussians and $textbfS$uperquadrics.
- Score: 16.446659867133977
- License:
- Abstract: Low-level 3D representations, such as point clouds, meshes, NeRFs, and 3D Gaussians, are commonly used to represent 3D objects or scenes. However, human perception typically understands 3D objects at a higher level as a composition of parts or structures rather than points or voxels. Representing 3D objects or scenes as semantic parts can benefit further understanding and applications. In this paper, we introduce $\textbf{PartGS}$, $\textbf{part}$-aware 3D reconstruction by a hybrid representation of 2D $\textbf{G}$aussians and $\textbf{S}$uperquadrics, which parses objects or scenes into semantic parts, digging 3D structural clues from multi-view image inputs. Accurate structured geometry reconstruction and high-quality rendering are achieved at the same time. Our method simultaneously optimizes superquadric meshes and Gaussians by coupling their parameters within our hybrid representation. On one hand, this hybrid representation inherits the advantage of superquadrics to represent different shape primitives, supporting flexible part decomposition of scenes. On the other hand, 2D Gaussians capture complex texture and geometry details, ensuring high-quality appearance and geometry reconstruction. Our method is fully unsupervised and outperforms existing state-of-the-art approaches in extensive experiments on DTU, ShapeNet, and real-life datasets.
Related papers
- Geometry Image Diffusion: Fast and Data-Efficient Text-to-3D with Image-Based Surface Representation [2.3213238782019316]
GIMDiffusion is a novel Text-to-3D model that utilizes geometry images to efficiently represent 3D shapes using 2D images.
We exploit the rich 2D priors of existing Text-to-Image models such as Stable Diffusion.
In short, GIMDiffusion enables the generation of 3D assets at speeds comparable to current Text-to-Image models.
arXiv Detail & Related papers (2024-09-05T17:21:54Z) - Semantic Gaussians: Open-Vocabulary Scene Understanding with 3D Gaussian Splatting [27.974762304763694]
We introduce Semantic Gaussians, a novel open-vocabulary scene understanding approach based on 3D Gaussian Splatting.
Unlike existing methods, we design a versatile projection approach that maps various 2D semantic features into a novel semantic component of 3D Gaussians.
We build a 3D semantic network that directly predicts the semantic component from raw 3D Gaussians for fast inference.
arXiv Detail & Related papers (2024-03-22T21:28:19Z) - GeoGS3D: Single-view 3D Reconstruction via Geometric-aware Diffusion Model and Gaussian Splatting [81.03553265684184]
We introduce GeoGS3D, a framework for reconstructing detailed 3D objects from single-view images.
We propose a novel metric, Gaussian Divergence Significance (GDS), to prune unnecessary operations during optimization.
Experiments demonstrate that GeoGS3D generates images with high consistency across views and reconstructs high-quality 3D objects.
arXiv Detail & Related papers (2024-03-15T12:24:36Z) - SceneWiz3D: Towards Text-guided 3D Scene Composition [134.71933134180782]
Existing approaches either leverage large text-to-image models to optimize a 3D representation or train 3D generators on object-centric datasets.
We introduce SceneWiz3D, a novel approach to synthesize high-fidelity 3D scenes from text.
arXiv Detail & Related papers (2023-12-13T18:59:30Z) - CC3D: Layout-Conditioned Generation of Compositional 3D Scenes [49.281006972028194]
We introduce CC3D, a conditional generative model that synthesizes complex 3D scenes conditioned on 2D semantic scene layouts.
Our evaluations on synthetic 3D-FRONT and real-world KITTI-360 datasets demonstrate that our model generates scenes of improved visual and geometric quality.
arXiv Detail & Related papers (2023-03-21T17:59:02Z) - 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) - DensePose 3D: Lifting Canonical Surface Maps of Articulated Objects to
the Third Dimension [71.71234436165255]
We contribute DensePose 3D, a method that can learn such reconstructions in a weakly supervised fashion from 2D image annotations only.
Because it does not require 3D scans, DensePose 3D can be used for learning a wide range of articulated categories such as different animal species.
We show significant improvements compared to state-of-the-art non-rigid structure-from-motion baselines on both synthetic and real data on categories of humans and animals.
arXiv Detail & Related papers (2021-08-31T18:33:55Z) - Learning Unsupervised Hierarchical Part Decomposition of 3D Objects from
a Single RGB Image [102.44347847154867]
We propose a novel formulation that allows to jointly recover the geometry of a 3D object as a set of primitives.
Our model recovers the higher level structural decomposition of various objects in the form of a binary tree of primitives.
Our experiments on the ShapeNet and D-FAUST datasets demonstrate that considering the organization of parts indeed facilitates reasoning about 3D geometry.
arXiv Detail & Related papers (2020-04-02T17:58:05Z)
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.