3D 视觉 - arXivDaily 专题

2311.17082 2024-05-21 cs.CV stat.ML 79%

DreamPropeller: Supercharge Text-to-3D Generation with Parallel Sampling

Linqi Zhou, Andy Shih, Chenlin Meng, Stefano Ermon

专题命中 3D生成：3D generation(title,abstract)；分类 cs.CV

Comments Github repo: https://github.com/alexzhou907/DreamPropeller; Project page: https://alexzhou907.github.io/dreampropeller_page/

2405.09874 2024-05-17 cs.CV 79%

Dual3D: Efficient and Consistent Text-to-3D Generation with Dual-mode Multi-view Latent Diffusion

Xinyang Li, Zhangyu Lai, Linning Xu, Jianfei Guo, Liujuan Cao, Shengchuan Zhang, Bo Dai, Rongrong Ji

专题命中 3D生成：3D generation(title,abstract)；分类 cs.CV

Comments Project Page: https://dual3d.github.io

2405.08055 2024-05-15 cs.CV 79%

DiffTF++: 3D-aware Diffusion Transformer for Large-Vocabulary 3D Generation

Ziang Cao, Fangzhou Hong, Tong Wu, Liang Pan, Ziwei Liu

专题命中 3D生成：3D generation(title,abstract)；分类 cs.CV

Comments arXiv admin note: substantial text overlap with arXiv:2309.07920

2403.02234 2024-05-08 cs.CV 79%

3DTopia: Large Text-to-3D Generation Model with Hybrid Diffusion Priors

Fangzhou Hong, Jiaxiang Tang, Ziang Cao, Min Shi, Tong Wu, Zhaoxi Chen, Shuai Yang, Tengfei Wang, Liang Pan, Dahua Lin, Ziwei Liu

专题命中 3D生成：3D generation(title,abstract)；分类 cs.CV

Comments Code available at https://github.com/3DTopia/3DTopia

2402.02972 2024-05-03 cs.CV cs.LG 79%

Retrieval-Augmented Score Distillation for Text-to-3D Generation

Junyoung Seo, Susung Hong, Wooseok Jang, Inès Hyeonsu Kim, Minseop Kwak, Doyup Lee, Seungryong Kim

专题命中 3D生成：3D generation(title,abstract)；分类 cs.CV

Comments Accepted to ICML 2024 / Project Page: https://ku-cvlab.github.io/ReDream/

2404.17419 2024-04-29 cs.CV 79%

Multi-view Image Prompted Multi-view Diffusion for Improved 3D Generation

Seungwook Kim, Yichun Shi, Kejie Li, Minsu Cho, Peng Wang

专题命中 3D生成：3D generation(title,abstract)；分类 cs.CV

Comments 5 pages including references, 2 figures, 2 tables

2308.16512 2024-04-19 cs.CV 79%

MVDream: Multi-view Diffusion for 3D Generation

Yichun Shi, Peng Wang, Jianglong Ye, Mai Long, Kejie Li, Xiao Yang

专题命中 3D生成：3D generation(title,abstract)；分类 cs.CV

Comments Reorganized for arXiv; Our project page is https://MV-Dream.github.io

2401.00909 2024-04-02 cs.CV cs.LG 79%

Taming Mode Collapse in Score Distillation for Text-to-3D Generation

Peihao Wang, Dejia Xu, Zhiwen Fan, Dilin Wang, Sreyas Mohan, Forrest Iandola, Rakesh Ranjan, Yilei Li, Qiang Liu, Zhangyang Wang, Vikas Chandra

专题命中 3D生成：3D generation(title,abstract)；分类 cs.CV

Comments Project page: https://vita-group.github.io/3D-Mode-Collapse/

2403.14966 2024-03-25 cs.CV 79%

DreamFlow: High-Quality Text-to-3D Generation by Approximating Probability Flow

Kyungmin Lee, Kihyuk Sohn, Jinwoo Shin

专题命中 3D生成：3D generation(title,abstract)；分类 cs.CV

Comments ICLR 2024

2403.13524 2024-03-21 cs.CV cs.AI 79%

Compress3D: a Compressed Latent Space for 3D Generation from a Single Image

Bowen Zhang, Tianyu Yang, Yu Li, Lei Zhang, Xi Zhao

专题命中 3D生成：3D generation(title,abstract)；分类 cs.CV

2403.12438 2024-03-20 cs.CV 79%

Precise-Physics Driven Text-to-3D Generation

Qingshan Xu, Jiao Liu, Melvin Wong, Caishun Chen, Yew-Soon Ong

专题命中 3D生成：3D generation(title,abstract)；分类 cs.CV

2403.10395 2024-03-18 cs.CV cs.LG 79%

Isotropic3D: Image-to-3D Generation Based on a Single CLIP Embedding

Pengkun Liu, Yikai Wang, Fuchun Sun, Jiafang Li, Hang Xiao, Hongxiang Xue, Xinzhou Wang

专题命中 3D生成：3D generation(title,abstract)；分类 cs.CV

Comments Project page: https://isotropic3d.github.io/ Source code: https://github.com/pkunliu/Isotropic3D

2403.09140 2024-03-15 cs.CV 79%

Sculpt3D: Multi-View Consistent Text-to-3D Generation with Sparse 3D Prior

Cheng Chen, Xiaofeng Yang, Fan Yang, Chengzeng Feng, Zhoujie Fu, Chuan-Sheng Foo, Guosheng Lin, Fayao Liu

专题命中 3D生成：3D generation(title,abstract)；分类 cs.CV

Comments Accepted by CVPR 2024. Project Page: https://stellarcheng.github.io/Sculpt3D/

2309.17175 2024-03-15 cs.CV 79%

TextField3D: Towards Enhancing Open-Vocabulary 3D Generation with Noisy Text Fields

Tianyu Huang, Yihan Zeng, Bowen Dong, Hang Xu, Songcen Xu, Rynson W. H. Lau, Wangmeng Zuo

专题命中 3D生成：3D generation(title,abstract)；分类 cs.CV

Comments Accepted by ICLR 2024

2312.09305 2024-02-08 cs.CV 79%

Stable Score Distillation for High-Quality 3D Generation

Boshi Tang, Jianan Wang, Zhiyong Wu, Lei Zhang

专题命中 3D生成：3D generation(title,abstract)；分类 cs.CV

2312.13271 2023-12-29 cs.CV 79%

Repaint123: Fast and High-quality One Image to 3D Generation with Progressive Controllable 2D Repainting

Junwu Zhang, Zhenyu Tang, Yatian Pang, Xinhua Cheng, Peng Jin, Yida Wei, Munan Ning, Li Yuan

专题命中 3D生成：3D generation(title,abstract)；分类 cs.CV

Comments Project page: https://pku-yuangroup.github.io/repaint123/

2312.04963 2023-12-11 cs.CV cs.AI 79%

Text-to-3D Generation with Bidirectional Diffusion using both 2D and 3D priors

Lihe Ding, Shaocong Dong, Zhanpeng Huang, Zibin Wang, Yiyuan Zhang, Kaixiong Gong, Dan Xu, Tianfan Xue

专题命中 3D生成：3D generation(title,abstract)；分类 cs.CV

2312.04806 2023-12-11 cs.CV 79%

RL Dreams: Policy Gradient Optimization for Score Distillation based 3D Generation

Aradhya N. Mathur, Phu Pham, Aniket Bera, Ojaswa Sharma

专题命中 3D生成：3D generation(title,abstract)；分类 cs.CV

2311.17971 2023-12-05 cs.CV 79%

GeoDream: Disentangling 2D and Geometric Priors for High-Fidelity and Consistent 3D Generation

Baorui Ma, Haoge Deng, Junsheng Zhou, Yu-Shen Liu, Tiejun Huang, Xinlong Wang

专题命中 3D生成：3D generation(title,abstract)；分类 cs.CV

Comments Code and Demo: https://github.com/baaivision/GeoDream

2311.15561 2023-11-28 cs.CV 79%

ET3D: Efficient Text-to-3D Generation via Multi-View Distillation

Yiming Chen, Zhiqi Li, Peidong Liu

专题命中 3D生成：3D generation(title,abstract)；分类 cs.CV

2309.14600 2023-09-27 cs.CV 79%

Progressive Text-to-3D Generation for Automatic 3D Prototyping

Han Yi, Zhedong Zheng, Xiangyu Xu, Tat-seng Chua

专题命中 3D生成：3D generation(title,abstract)；分类 cs.CV

2305.15808 2023-05-26 cs.CV 79%

Towards Language-guided Interactive 3D Generation: LLMs as Layout Interpreter with Generative Feedback

Yiqi Lin, Hao Wu, Ruichen Wang, Haonan Lu, Xiaodong Lin, Hui Xiong, Lin Wang

专题命中 3D生成：3D generation(title,abstract)；分类 cs.CV

Comments Preprint. Work in Progres

1912.10787 2020-01-28 cs.GR cs.LG stat.ML 79%

Learned Interpolation for 3D Generation

Austin Dill, Songwei Ge, Eunsu Kang, Chun-Liang Li, Barnabas Poczos

专题命中 3D生成：3D generation(title)；point cloud(abstract)；分类 cs.GR

Comments Creativity and Design Workshop at NeurIPS 2019

2405.10988 2024-07-30 cs.LG cs.AI 78%

Flow Score Distillation for Diverse Text-to-3D Generation

Runjie Yan, Kailu Wu, Kaisheng Ma

专题命中 3D生成：3D generation(title,abstract)

Comments Consistent Flow Distillation is an improved version of this paper

2507.05256 2025-08-05 cs.CV 77%

SegmentDreamer: Towards High-fidelity Text-to-3D Synthesis with Segmented Consistency Trajectory Distillation

Jiahao Zhu, Zixuan Chen, Guangcong Wang, Xiaohua Xie, Yi Zhou

机构 * Sun Yat-sen University（中山大学）； Great Bay University（大贝大学）； Pazhou Lab (Huangpu)（琶洲实验室）； Guangdong Province Key Laboratory of Information Security Technology（广东省信息安全技术重点实验室）

专题命中 3D生成：Gaussian Splatting(abstract)；3DGS(abstract)；3D generation(abstract)；分类 cs.CV

Comments Accepted by ICCV 2025, project page: https://zjhjojo.github.io/segmentdreamer/

2607.10826 2026-07-14 cs.CV cs.AI cs.GR 新提交 76%

3D-DefectBench: A Controlled Factorial Study of Vision-Language Model Evaluation Pipelines for Fine-Grained 3D Generation Defects

3D-缺陷基准：用于细粒度3D生成缺陷的视觉语言模型评估管道的控制因子研究

Zhenyu Zhao, Nanshan Jia, Jihyeon Je, Yifu Tang, Alvin Chan, Michael Spedden, Michael V. Palleschi, Sui Huang, Jingshen Wang, Zeyu Zheng

机构 * Roblox Corporation（罗布乐思公司）； Berkeley AI Research Lab & Department of Industrial Engineering and Operations Research, University of California, Berkeley（加州大学伯克利分校伯克利人工智能研究实验室及工业工程与运筹学系）； Computer Science Department, Stanford University（斯坦福大学计算机科学系）； Division of Biostatistics, University of California, Berkeley（加州大学伯克利分校生物统计学系）

专题命中 3D生成：3D generation(title)；分类 cs.CV、cs.GR

AI总结研究基于视觉语言模型的3D缺陷检测管道评估，引入3D-DefectBench基准框架，通过平衡因子设计改变多个管道因素进行实验，发现模型选择影响最大，各因素相互作用，还得出一些协议表现及评判与人工标注对比情况等结论。

2605.13852 2026-05-15 cs.GR cs.CV cs.LG 76%

Realiz3D: 3D Generation Made Photorealistic via Domain-Aware Learning

Realiz3D: 通过领域感知学习实现逼真3D生成

Ido Sobol, Kihyuk Sohn, Yoav Blum, Egor Zakharov, Max Bluvstein, Andrea Vedaldi, Or Litany

机构 * Technion（技术学院）； Meta AI

专题命中 3D生成：3D generation(title)；分类 cs.CV、cs.GR

AI总结 Realiz3D通过分离控制信号与视觉领域，提升生成图像的逼真度和3D一致性，适用于文本到多视角生成和3D输入纹理生成。

Comments Accepted to CVPR 2026. Project page: https://idosobol.github.io/realiz3d/

2510.08656 2025-10-13 cs.GR cs.AI cs.CV 76%

A 3D Generation Framework from Cross Modality to Parameterized Primitive

Yiming Liang, Huan Yu, Zili Wang, Shuyou Zhang, Guodong Yi, Jin Wang, Jianrong Tan

机构 * Zhejiang University（浙江大学）； Robotics Research Center of Yuyao City（余姚市机器人研究中心）

专题命中 3D生成：3D generation(title)；分类 cs.CV、cs.GR

2509.25079 2025-09-30 cs.CV cs.AI cs.GR 76%

UniLat3D: Geometry-Appearance Unified Latents for Single-Stage 3D Generation

Guanjun Wu, Jiemin Fang, Chen Yang, Sikuang Li, Taoran Yi, Jia Lu, Zanwei Zhou, Jiazhong Cen, Lingxi Xie, Xiaopeng Zhang, Wei Wei, Wenyu Liu, Xinggang Wang, Qi Tian

机构 * Huawei Inc.（华为公司）； Huazhong University of Science and Technology（华中科技大学）； Shanghai Jiaotong University（上海交通大学）

专题命中 3D生成：3D generation(title)；分类 cs.CV、cs.GR

Comments Project page: https://unilat3d.github.io/

2406.18581 2025-02-14 cs.CV cs.GR 76%

Dream-in-Style: Text-to-3D Generation Using Stylized Score Distillation

Hubert Kompanowski, Binh-Son Hua

专题命中 3D生成：3D generation(title)；分类 cs.CV、cs.GR

1. 3D生成 447 篇

DreamPropeller: Supercharge Text-to-3D Generation with Parallel Sampling

Dual3D: Efficient and Consistent Text-to-3D Generation with Dual-mode Multi-view Latent Diffusion

DiffTF++: 3D-aware Diffusion Transformer for Large-Vocabulary 3D Generation

3DTopia: Large Text-to-3D Generation Model with Hybrid Diffusion Priors

Retrieval-Augmented Score Distillation for Text-to-3D Generation

Multi-view Image Prompted Multi-view Diffusion for Improved 3D Generation

MVDream: Multi-view Diffusion for 3D Generation

Taming Mode Collapse in Score Distillation for Text-to-3D Generation

DreamFlow: High-Quality Text-to-3D Generation by Approximating Probability Flow

Compress3D: a Compressed Latent Space for 3D Generation from a Single Image

Precise-Physics Driven Text-to-3D Generation

Isotropic3D: Image-to-3D Generation Based on a Single CLIP Embedding

Sculpt3D: Multi-View Consistent Text-to-3D Generation with Sparse 3D Prior

TextField3D: Towards Enhancing Open-Vocabulary 3D Generation with Noisy Text Fields

Stable Score Distillation for High-Quality 3D Generation

Repaint123: Fast and High-quality One Image to 3D Generation with Progressive Controllable 2D Repainting

Text-to-3D Generation with Bidirectional Diffusion using both 2D and 3D priors

RL Dreams: Policy Gradient Optimization for Score Distillation based 3D Generation

GeoDream: Disentangling 2D and Geometric Priors for High-Fidelity and Consistent 3D Generation

ET3D: Efficient Text-to-3D Generation via Multi-View Distillation

Progressive Text-to-3D Generation for Automatic 3D Prototyping

Towards Language-guided Interactive 3D Generation: LLMs as Layout Interpreter with Generative Feedback

Learned Interpolation for 3D Generation

Flow Score Distillation for Diverse Text-to-3D Generation

SegmentDreamer: Towards High-fidelity Text-to-3D Synthesis with Segmented Consistency Trajectory Distillation

3D-DefectBench: A Controlled Factorial Study of Vision-Language Model Evaluation Pipelines for Fine-Grained 3D Generation Defects

Realiz3D: 3D Generation Made Photorealistic via Domain-Aware Learning

A 3D Generation Framework from Cross Modality to Parameterized Primitive

UniLat3D: Geometry-Appearance Unified Latents for Single-Stage 3D Generation

Dream-in-Style: Text-to-3D Generation Using Stylized Score Distillation