3D 视觉 - arXivDaily 专题

2409.07454 2024-09-12 cs.CV cs.MM 83%

DreamMesh: Jointly Manipulating and Texturing Triangle Meshes for Text-to-3D Generation

Haibo Yang, Yang Chen, Yingwei Pan, Ting Yao, Zhineng Chen, Zuxuan Wu, Yu-Gang Jiang, Tao Mei

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

Comments ECCV 2024. Project page is available at \url{https://dreammesh.github.io}

2408.10935 2024-08-21 cs.CV 83%

Large Point-to-Gaussian Model for Image-to-3D Generation

Longfei Lu, Huachen Gao, Tao Dai, Yaohua Zha, Zhi Hou, Junta Wu, Shu-Tao Xia

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

Comments 10 pages, 9 figures, ACM MM 2024

2407.19548 2024-07-30 cs.CV 83%

Cycle3D: High-quality and Consistent Image-to-3D Generation via Generation-Reconstruction Cycle

Zhenyu Tang, Junwu Zhang, Xinhua Cheng, Wangbo Yu, Chaoran Feng, Yatian Pang, Bin Lin, Li Yuan

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

Comments Project page: https://pku-yuangroup.github.io/Cycle3D/

2407.16260 2024-07-24 cs.CV 83%

DreamDissector: Learning Disentangled Text-to-3D Generation from 2D Diffusion Priors

Zizheng Yan, Jiapeng Zhou, Fanpeng Meng, Yushuang Wu, Lingteng Qiu, Zisheng Ye, Shuguang Cui, Guanying Chen, Xiaoguang Han

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

Comments ECCV 2024. Project page: https://chester256.github.io/dreamdissector

2406.10000 2024-06-17 cs.CV 83%

OrientDream: Streamlining Text-to-3D Generation with Explicit Orientation Control

Yuzhong Huang, Zhong Li, Zhang Chen, Zhiyuan Ren, Guosheng Lin, Fred Morstatter, Yi Xu

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

2405.11252 2024-05-21 cs.CV 83%

Dreamer XL: Towards High-Resolution Text-to-3D Generation via Trajectory Score Matching

Xingyu Miao, Haoran Duan, Varun Ojha, Jun Song, Tejal Shah, Yang Long, Rajiv Ranjan

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

2405.06461 2024-05-15 cs.GR 83%

SketchDream: Sketch-based Text-to-3D Generation and Editing

Feng-Lin Liu, Hongbo Fu, Yu-Kun Lai, Lin Gao

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

2310.02977 2024-04-18 cs.CV cs.CL cs.LG 83%

T$^3$Bench: Benchmarking Current Progress in Text-to-3D Generation

Yuze He, Yushi Bai, Matthieu Lin, Wang Zhao, Yubin Hu, Jenny Sheng, Ran Yi, Juanzi Li, Yong-Jin Liu

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

Comments Under review

2404.06091 2024-04-10 cs.CV 83%

Hash3D: Training-free Acceleration for 3D Generation

Xingyi Yang, Xinchao Wang

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

Comments https://adamdad.github.io/hash3D/

2403.17001 2024-03-26 cs.CV cs.MM 83%

VP3D: Unleashing 2D Visual Prompt for Text-to-3D Generation

Yang Chen, Yingwei Pan, Haibo Yang, Ting Yao, Tao Mei

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

Comments CVPR 2024; Project page: https://vp3d-cvpr24.github.io

2312.06439 2024-03-13 cs.CV 83%

DreamControl: Control-Based Text-to-3D Generation with 3D Self-Prior

Tianyu Huang, Yihan Zeng, Zhilu Zhang, Wan Xu, Hang Xu, Songcen Xu, Rynson W. H. Lau, Wangmeng Zuo

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

Comments Accepted by CVPR 2024

2305.18766 2024-03-12 cs.CV cs.AI cs.LG 83%

HiFA: High-fidelity Text-to-3D Generation with Advanced Diffusion Guidance

Junzhe Zhu, Peiye Zhuang, Sanmi Koyejo

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

Comments Project page: https://hifa-team.github.io/HiFA-site/

2303.07937 2024-02-07 cs.CV 83%

Let 2D Diffusion Model Know 3D-Consistency for Robust Text-to-3D Generation

Junyoung Seo, Wooseok Jang, Min-Seop Kwak, Hyeonsu Kim, Jaehoon Ko, Junho Kim, Jin-Hwa Kim, Jiyoung Lee, Seungryong Kim

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

Comments Project page https://ku-cvlab.github.io/3DFuse/

2401.14257 2024-01-30 cs.CV cs.AI 83%

Sketch2NeRF: Multi-view Sketch-guided Text-to-3D Generation

Minglin Chen, Weihao Yuan, Yukun Wang, Zhe Sheng, Yisheng He, Zilong Dong, Liefeng Bo, Yulan Guo

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

Comments 11 pages, 9 figures

2312.11774 2023-12-20 cs.CV 83%

Text-Image Conditioned Diffusion for Consistent Text-to-3D Generation

Yuze He, Yushi Bai, Matthieu Lin, Jenny Sheng, Yubin Hu, Qi Wang, Yu-Hui Wen, Yong-Jin Liu

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

2305.16213 2023-11-23 cs.LG cs.CV 83%

ProlificDreamer: High-Fidelity and Diverse Text-to-3D Generation with Variational Score Distillation

Zhengyi Wang, Cheng Lu, Yikai Wang, Fan Bao, Chongxuan Li, Hang Su, Jun Zhu

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

Comments NeurIPS 2023 (Spotlight)

2311.05461 2023-11-10 cs.CV cs.MM 83%

Control3D: Towards Controllable Text-to-3D Generation

Yang Chen, Yingwei Pan, Yehao Li, Ting Yao, Tao Mei

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

Comments ACM Multimedia 2023

2307.16605 2023-10-23 cs.CV 83%

VPP: Efficient Conditional 3D Generation via Voxel-Point Progressive Representation

Zekun Qi, Muzhou Yu, Runpei Dong, Kaisheng Ma

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

Comments Accepted at NeurIPS 2023

2309.03599 2023-09-08 cs.CV 83%

Chasing Consistency in Text-to-3D Generation from a Single Image

Yichen Ouyang, Wenhao Chai, Jiayi Ye, Dapeng Tao, Yibing Zhan, Gaoang Wang

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

Comments 9 pages, 11 figures

2305.15753 2023-05-26 cs.CV 83%

T2TD: Text-3D Generation Model based on Prior Knowledge Guidance

Weizhi Nie, Ruidong Chen, Weijie Wang, Bruno Lepri, Nicu Sebe

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

2503.16278 2025-10-10 cs.LG cond-mat.mtrl-sci q-bio.BM 82%

Unified Cross-Scale 3D Generation and Understanding via Autoregressive Modeling

Shuqi Lu, Haowei Lin, Lin Yao, Zhifeng Gao, Xiaohong Ji, Yitao Liang, Weinan E, Linfeng Zhang, Guolin Ke

机构 * DP Technology（DP技术公司）； AI for Science Institute（人工智能科学研究院）； School of Mathematical Sciences（数学科学学院）； Center for Machine Learning Research（机器学习研究中心）； Institute for Artificial Intelligence（人工智能研究院）

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

2606.04108 2026-06-04 cs.GR cs.AI cs.CV cs.LG 81%

SymTRELLIS: Symmetry-Enforced Voxel Latents for 3D Generation

SymTRELLIS: 对称性增强的体素潜变量用于3D生成

Guangda Ji, Qimin Chen, Qinchan Li, Mingrui Zhao, Kai Wang, Hao Zhang

机构 * Simon Fraser University（西蒙 Fraser大学）

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

AI总结提出SymTRELLIS方法，通过在流模型生成过程中对预测速度进行对称化平均，强制任意有限点群对称性，无需重新训练VAE或流模型，显著降低对称性误差。

2605.21121 2026-05-21 cs.CV cs.GR 81%

ROAR-3D: Routing Arbitrary Views for High-Fidelity 3D Generation

ROAR-3D: 为高保真3D生成实现任意视角路由

Hanxiao Sun, Mingxin Yang, Shuhui Yang, Zebin He, Xintong Han, Hongbo Fu, Chunchao Guo, Wenhan Luo

机构 * The Hong Kong University of Science and Technology（香港科学与技术大学）； Tencent Hunyuan（腾讯文生）

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

AI总结本文提出ROAR-3D方法，通过改进预训练单视角模型以支持任意数量的未置位图像，利用视图路由和双流注意力设计实现高效的多视角3D生成，显著提升生成质量并支持测试时视角扩展。

2604.26509 2026-05-11 cs.RO cs.CV 81%

3D Generation for Embodied AI and Robotic Simulation: A Survey

用于具身AI和机器人模拟的3D生成：综述

Tianwei Ye, Yifan Mao, Minwen Liao, Jian Liu, Chunchao Guo, Dazhao Du, Quanxin Shou, Fangqi Zhu, Song Guo

机构 * Hong Kong University of Science and Technology（香港科技大学）； Wuhan University（武汉大学）； Harbin Institute of Technology（哈尔滨工业大学）； Xinjiang University（新疆大学）； Tencent（腾讯）

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

AI总结本文综述了用于具身AI的3D生成，探讨了其在数据生成、模拟环境构建和Sim2Real桥梁中的作用，指出领域正从视觉真实转向交互准备，并识别了物理标注有限、几何质量与物理有效性差距等主要瓶颈。

Comments 27 pages, 11 figures, 8 tables

2601.12234 2026-01-21 cs.GR cs.AI cs.CV 81%

Proc3D: Procedural 3D Generation and Parametric Editing of 3D Shapes with Large Language Models

Proc3D: 基于大语言模型的3D形状过程生成与参数编辑

Fadlullah Raji, Stefano Petrangeli, Matheus Gadelha, Yu Shen, Uttaran Bhattacharya, Gang Wu

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

AI总结 Proc3D利用大语言模型实现3D形状的可编辑生成，通过参数化编辑提升设计效率和准确性。

2512.03052 2025-12-04 cs.GR cs.CV 81%

LATTICE: Democratize High-Fidelity 3D Generation at Scale

LATTICE：大规模实现高保真3D生成

Zeqiang Lai, Yunfei Zhao, Zibo Zhao, Haolin Liu, Qingxiang Lin, Jingwei Huang, Chunchao Guo, Xiangyu Yue

机构 * MMLab, CUHK（CUHK人工智能实验室）； Tencent Hunyuan（腾讯文言）

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

AI总结 LATTICE通过VoxSet半结构化表示实现高效高保真3D生成，支持任意分辨率解码和灵活推理，达到最先进的性能。

Comments Technical Report

2510.08271 2025-11-04 cs.GR cs.CV cs.LG 81%

SViM3D: Stable Video Material Diffusion for Single Image 3D Generation

Andreas Engelhardt, Mark Boss, Vikram Voleti, Chun-Han Yao, Hendrik P. A. Lensch, Varun Jampani

机构 * Stability AI ； University of Tübingen（图宾根大学）

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

Comments Accepted by International Conference on Computer Vision (ICCV 2025). Project page: http://svim3d.aengelhardt.com

2506.07932 2025-06-10 cs.GR cs.CV cs.LG 81%

Squeeze3D: Your 3D Generation Model is Secretly an Extreme Neural Compressor

Rishit Dagli, Yushi Guan, Sankeerth Durvasula, Mohammadreza Mofayezi, Nandita Vijaykumar

机构 * University of Toronto（多伦多大学）

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

2412.09648 2024-12-16 eess.IV cs.CV cs.GR cs.LG 81%

DSplats: 3D Generation by Denoising Splats-Based Multiview Diffusion Models

Kevin Miao, Harsh Agrawal, Qihang Zhang, Federico Semeraro, Marco Cavallo, Jiatao Gu, Alexander Toshev

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

2412.06785 2024-12-10 cs.CV cs.GR 81%

Tactile DreamFusion: Exploiting Tactile Sensing for 3D Generation

Ruihan Gao, Kangle Deng, Gengshan Yang, Wenzhen Yuan, Jun-Yan Zhu

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

Comments Accepted to NeurIPS 2024. Project webpage: https://ruihangao.github.io/TactileDreamFusion/ Code: https://github.com/RuihanGao/TactileDreamFusion

1. 3D生成 447 篇

DreamMesh: Jointly Manipulating and Texturing Triangle Meshes for Text-to-3D Generation

Large Point-to-Gaussian Model for Image-to-3D Generation

Cycle3D: High-quality and Consistent Image-to-3D Generation via Generation-Reconstruction Cycle

DreamDissector: Learning Disentangled Text-to-3D Generation from 2D Diffusion Priors

OrientDream: Streamlining Text-to-3D Generation with Explicit Orientation Control

Dreamer XL: Towards High-Resolution Text-to-3D Generation via Trajectory Score Matching

SketchDream: Sketch-based Text-to-3D Generation and Editing

T$^3$Bench: Benchmarking Current Progress in Text-to-3D Generation

Hash3D: Training-free Acceleration for 3D Generation

VP3D: Unleashing 2D Visual Prompt for Text-to-3D Generation

DreamControl: Control-Based Text-to-3D Generation with 3D Self-Prior

HiFA: High-fidelity Text-to-3D Generation with Advanced Diffusion Guidance

Let 2D Diffusion Model Know 3D-Consistency for Robust Text-to-3D Generation

Sketch2NeRF: Multi-view Sketch-guided Text-to-3D Generation

Text-Image Conditioned Diffusion for Consistent Text-to-3D Generation

ProlificDreamer: High-Fidelity and Diverse Text-to-3D Generation with Variational Score Distillation

Control3D: Towards Controllable Text-to-3D Generation

VPP: Efficient Conditional 3D Generation via Voxel-Point Progressive Representation

Chasing Consistency in Text-to-3D Generation from a Single Image

T2TD: Text-3D Generation Model based on Prior Knowledge Guidance

Unified Cross-Scale 3D Generation and Understanding via Autoregressive Modeling

SymTRELLIS: Symmetry-Enforced Voxel Latents for 3D Generation

ROAR-3D: Routing Arbitrary Views for High-Fidelity 3D Generation

3D Generation for Embodied AI and Robotic Simulation: A Survey

Proc3D: Procedural 3D Generation and Parametric Editing of 3D Shapes with Large Language Models

LATTICE: Democratize High-Fidelity 3D Generation at Scale

SViM3D: Stable Video Material Diffusion for Single Image 3D Generation

Squeeze3D: Your 3D Generation Model is Secretly an Extreme Neural Compressor

DSplats: 3D Generation by Denoising Splats-Based Multiview Diffusion Models

Tactile DreamFusion: Exploiting Tactile Sensing for 3D Generation