CGGS: Consistency-Augmented Geometric Gaussian Splatting for Ego-centric 3D Scene Generation
Summary
CGGS is a text-to-3D framework that improves geometric consistency and quality in ego-centric 3D scene generation using a multi-stage approach with consistency-augmented loss, layout decoration, and geometric refinement via entropy-based depth loss.
View Cached Full Text
Cached at: 07/08/26, 06:48 AM
Paper page - CGGS: Consistency-Augmented Geometric Gaussian Splatting for Ego-centric 3D Scene Generation
Source: https://huggingface.co/papers/2607.03819
Abstract
CGGS is a text-to-3D framework that enhances 3D-content-awareness and addresses geometric distortions through a multi-stage approach involving ego-centric generation, layout decoration, and geometric refinement.
Challenges remain in ego-centric 3D scene generation due to limited view overlap and the dominant influence of individual perspectives on scene interpretation. These factors hinder the creation of viewpoint-consistent and semantically aligned visual content, as well as the construction of accurate geometric structures. In this paper, we propose CGGS, a text-to-3D framework aiming to enhance 3D-content-awareness and address geometric distortions in ego-centric scene generation. Firstly, the Ego-centric Generator is proposed by fine-tuning aMulti-View Latent Diffusion Modelwithconsistency-augmented lossto generate consistent, high-fidelity 2D content aligned with textual descriptions. Then, Layout Decorator leveragesoptical flowandpoint-track correspondenceto estimate depth, therefore producingdense point cloudsas coarse layouts from the ego-centric 2D priors. Building on this initialization, Geometric Refiner is proposed to enhance3D Gaussian reconstructionvia anentropy-based Mutual Information Depth Loss(MID) combined with ahierarchical optimization schemefor improving visual quality and geometric structure. Comprehensive experiments demonstrate that softred{CGGS} outperforms previous methods in generating coherent and accurate text-driven 3D scenes. Project page: https://cggs-26.github.io/cggs26/.
View arXiv pageView PDFProject pageGitHub6Add to collection
Get this paper in your agent:
hf papers read 2607\.03819
Don’t have the latest CLI?curl \-LsSf https://hf\.co/cli/install\.sh \| bash
Models citing this paper0
No model linking this paper
Cite arxiv.org/abs/2607.03819 in a model README.md to link it from this page.
Datasets citing this paper0
No dataset linking this paper
Cite arxiv.org/abs/2607.03819 in a dataset README.md to link it from this page.
Spaces citing this paper0
No Space linking this paper
Cite arxiv.org/abs/2607.03819 in a Space README.md to link it from this page.
Collections including this paper0
No Collection including this paper
Add this paper to acollectionto link it from this page.
Similar Articles
GlobalSplat: Efficient Feed-Forward 3D Gaussian Splatting via Global Scene Tokens
GlobalSplat introduces an efficient feed-forward framework for 3D Gaussian splatting that achieves compact and consistent scene reconstruction using global scene tokens, reducing computational overhead and inference time to under 78ms. The method uses a coarse-to-fine training approach to prevent representation bloat while maintaining competitive novel-view synthesis performance with significantly fewer Gaussians (16K) compared to dense baselines.
ZipSplat: Fewer Gaussians, Better Splats
ZipSplat is a token-based feed-forward 3D Gaussian Splatting model that uses k-means clustering to decouple Gaussian placement from the pixel grid, achieving ~6x fewer Gaussians while setting new state-of-the-art results on DL3DV and RealEstate10K without requiring ground-truth poses or intrinsics.
FLAT: Feedforward Latent Triangle Splatting for Geometrically Accurate Scene Generation
FLAT proposes a method to decode explicit triangle splats directly from video diffusion latents for geometrically accurate 3D scene generation. It introduces a ray-centered rotation parameterization and a product window function to improve gradient flow, achieving better geometric accuracy than prior feedforward methods while supporting real-time rendering.
Sat3DGen: Comprehensive Street-Level 3D Scene Generation from Single Satellite Image
Sat3DGen introduces a geometry-first approach for generating street-level 3D scenes from a single satellite image, achieving improved geometric accuracy and photorealism through novel constraints and training strategies. The method demonstrates significant improvements over prior work on the VIGOR-OOD benchmark.
Multi4D: High-Fidelity Dynamic Gaussian Splatting via Multi-Level Competitive Allocation
Multi4D introduces a multi-level competitive allocation framework for dynamic 3D Gaussian splatting that balances motion consistency and visual fidelity, achieving state-of-the-art rendering quality and real-time performance.