paper-with-me

홈 › Papers

DreamPolisher: Towards High-Quality Text-to-3D Generation via Geometric Diffusion

2024-03-25 · Yuanze Lin, Ronald Clark, Philip Torr

We present DreamPolisher, a novel Gaussian Splatting based method with geometric guidance, tailored to learn cross-view consistency and intricate detail from textual descriptions. While recent progress on text-to-3D generation methods have been promising, prevailing methods often fail to ensure view-consistency and textural richness. This problem becomes particularly noticeable for methods that work with text input alone. To address this, we propose a two-stage Gaussian Splatting based approach that enforces geometric consistency among views. Initially, a coarse 3D generation undergoes refinement via geometric optimization. Subsequently, we use a ControlNet driven refiner coupled with the geometric consistency term to improve both texture fidelity and overall consistency of the generated 3D asset. Empirical evaluations across diverse textual prompts spanning various object categories demonstrate the efficacy of DreamPolisher in generating consistent and realistic 3D objects, aligning closely with the semantics of the textual instructions.

📄 PDF Abstract BibTeX arXiv:2403.17237

Code (0)

등록된 구현이 없습니다.

Tasks

3D GenerationText to 3D

Similar Papers 제목 키워드 기반

Deep Geometric Moments Promote Shape Consistency in Text-to-3D Generation

2024-08-12 · Utkarsh Nath, Rajeev Goel, Eun Som Jeon, Changhoon Kim 외

To address the data scarcity associated with 3D assets, 2D-lifting techniques such as Score Distillation Sampling (SDS) have become a widely adopted practice in text-to-3D generation pipelines. However, the diffusion mod…

3D GenerationText to 3D

GeoDiffusion: Text-Prompted Geometric Control for Object Detection Data Generation

2023-06-07 · Kai Chen, Enze Xie, Zhe Chen, Yibo Wang 외

Diffusion models have attracted significant attention due to the remarkable ability to create content and generate data for tasks like image classification. However, the usage of diffusion models to generate the high-qua…

image-classificationImage ClassificationImage GenerationLayout-to-Image Generation+2

GeoLoom: High-quality Geometric Diagram Generation from Textual Input

2025-12-09 · Xiaojing Wei, Ting Zhang, Wei He, Jingdong Wang 외 arxiv

High-quality geometric diagram generation presents both a challenge and an opportunity: it demands strict spatial accuracy while offering well-defined constraints to guide generation. Inspired by recent advances in geome…

LSS3D: Learnable Spatial Shifting for Consistent and High-Quality 3D Generation from Single-Image

2025-11-15 · Zhuojiang Cai, Yiheng Zhang, Meitong Guo, Mingdao Wang 외 arxiv

Recently, multi-view diffusion-based 3D generation methods have gained significant attention. However, these methods often suffer from shape and texture misalignment across generated multi-view images, leading to low-qua…

3D Generation

TexSpot: 3D Texture Enhancement with Spatially-uniform Point Latent Representation

2026-02-12 · Ziteng Lu, Yushuang Wu, Chongjie Ye, Yuda Qiu 외 arxiv

High-quality 3D texture generation remains a fundamental challenge due to the view-inconsistency inherent in current mainstream multi-view diffusion pipelines. Existing representations either rely on UV maps, which suffe…