CompGS: Unleashing 2D Compositionality for Compositional Text-to-3D via Dynamically Optimizing 3D Gaussians

• URL: http://arxiv.org/abs/2410.20723v1
• Date: Mon, 28 Oct 2024 04:35:14 GMT
• Title: CompGS: Unleashing 2D Compositionality for Compositional Text-to-3D via Dynamically Optimizing 3D Gaussians
• Authors: Chongjian Ge, Chenfeng Xu, Yuanfeng Ji, Chensheng Peng, Masayoshi Tomizuka, Ping Luo, Mingyu Ding, Varun Jampani, Wei Zhan,
• Abstract summary: CompGS is a novel generative framework that employs 3D Gaussian Splatting (GS) for efficient, compositional text-to-3D content generation. CompGS can be easily extended to controllable 3D editing, facilitating scene generation.
• Score: 97.15119679296954
• License:
• Abstract: Recent breakthroughs in text-guided image generation have significantly advanced the field of 3D generation. While generating a single high-quality 3D object is now feasible, generating multiple objects with reasonable interactions within a 3D space, a.k.a. compositional 3D generation, presents substantial challenges. This paper introduces CompGS, a novel generative framework that employs 3D Gaussian Splatting (GS) for efficient, compositional text-to-3D content generation. To achieve this goal, two core designs are proposed: (1) 3D Gaussians Initialization with 2D compositionality: We transfer the well-established 2D compositionality to initialize the Gaussian parameters on an entity-by-entity basis, ensuring both consistent 3D priors for each entity and reasonable interactions among multiple entities; (2) Dynamic Optimization: We propose a dynamic strategy to optimize 3D Gaussians using Score Distillation Sampling (SDS) loss. CompGS first automatically decomposes 3D Gaussians into distinct entity parts, enabling optimization at both the entity and composition levels. Additionally, CompGS optimizes across objects of varying scales by dynamically adjusting the spatial parameters of each entity, enhancing the generation of fine-grained details, particularly in smaller entities. Qualitative comparisons and quantitative evaluations on T3Bench demonstrate the effectiveness of CompGS in generating compositional 3D objects with superior image quality and semantic alignment over existing methods. CompGS can also be easily extended to controllable 3D editing, facilitating scene generation. We hope CompGS will provide new insights to the compositional 3D generation. Project page: https://chongjiange.github.io/compgs.html.

Related papers

• Learning Part-aware 3D Representations by Fusing 2D Gaussians and Superquadrics [16.446659867133977]
  Low-level 3D representations, such as point clouds, meshes, NeRFs, and 3D Gaussians, are commonly used to represent 3D objects or scenes. We aim to solve part-aware 3D reconstruction, which parses objects or scenes into semantic parts.
  arXiv  Detail & Related papers  (2024-08-20T12:30:37Z)
• ComboVerse: Compositional 3D Assets Creation Using Spatially-Aware Diffusion Guidance [76.7746870349809]
  We present ComboVerse, a 3D generation framework that produces high-quality 3D assets with complex compositions by learning to combine multiple models. Our proposed framework emphasizes spatial alignment of objects, compared with standard score distillation sampling.
  arXiv  Detail & Related papers  (2024-03-19T03:39:43Z)
• GALA3D: Towards Text-to-3D Complex Scene Generation via Layout-guided Generative Gaussian Splatting [52.150502668874495]
  We present GALA3D, generative 3D GAussians with LAyout-guided control, for effective compositional text-to-3D generation. GALA3D is a user-friendly, end-to-end framework for state-of-the-art scene-level 3D content generation and controllable editing.
  arXiv  Detail & Related papers  (2024-02-11T13:40:08Z)
• SAGD: Boundary-Enhanced Segment Anything in 3D Gaussian via Gaussian Decomposition [66.80822249039235]
  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)
• AGG: Amortized Generative 3D Gaussians for Single Image to 3D [108.38567665695027]
  We introduce an Amortized Generative 3D Gaussian framework (AGG) that instantly produces 3D Gaussians from a single image. AGG decomposes the generation of 3D Gaussian locations and other appearance attributes for joint optimization. We propose a cascaded pipeline that first generates a coarse representation of the 3D data and later upsamples it with a 3D Gaussian super-resolution module.
  arXiv  Detail & Related papers  (2024-01-08T18:56:33Z)
• Text-to-3D using Gaussian Splatting [18.163413810199234]
  This paper proposes GSGEN, a novel method that adopts Gaussian Splatting, a recent state-of-the-art representation, to text-to-3D generation. GSGEN aims at generating high-quality 3D objects and addressing existing shortcomings by exploiting the explicit nature of Gaussian Splatting. Our approach can generate 3D assets with delicate details and accurate geometry.
  arXiv  Detail & Related papers  (2023-09-28T16:44:31Z)
• 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)

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.