arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~

大厂专区

Horizon Robotics(地平线机器人)

2026-04-07 至 2026-04-07 共收录 2
2604.04406 2026-04-07 cs.CV

3D-Fixer: Coarse-to-Fine In-place Completion for 3D Scenes from a Single Image

3D-Fixer:从单张图像生成3D场景的粗到细就地补全

Ze-Xin Yin, Liu Liu, Xinjie Wang, Wei Sui, Zhizhong Su, Jian Yang, Jin Xie

机构 * College of Computer Science, Nankai University(南开大学计算机科学学院) School of Intelligence Science and Technology, Nanjing University(南京大学智能科学与技术学院) Horizon Robotics(地平线机器人) D-Robotics

AI总结 本文提出3D-Fixer,通过粗到细的生成方案解决单张图像生成3D场景的布局和3D资产恢复问题,结合双分支条件网络和Occlusion-Robust Feature Alignment策略,提升生成精度和效率,同时引入ARSG-110K数据集提升训练效果。

Comments 17 pages, 10 figures, CVPR 2026, project page: https://zx-yin.github.io/3dfixer

详情

展开后加载摘要…

URL PDF HTML 收藏
2509.07435 2026-04-07 cs.CV

DreamLifting: A Plug-in Module Lifting MV Diffusion Models for 3D Asset Generation

DreamLifting:一种插件模块用于提升MV扩散模型以生成3D资产

Ze-Xin Yin, Jiaxiong Qiu, Liu Liu, Xinjie Wang, Wei Sui, Zhizhong Su, Jian Yang, Jin Xie

机构 * PCA Lab, VCIP, College of Computer Science, Nankai University(南开大学计算机学院VCIP实验室PCA Lab) School of Intelligence Science and Technology, Nanjing University(南京大学智能科学与技术学院) Horizon Robotics(地平线机器人) D-Robotics

AI总结 本文提出LGAA框架,通过多视角扩散先验统一几何与PBR材质建模,结合模块化设计和改进的VAE实现高效3D资产生成,实验表明其在文本和图像条件下均表现优异。

Comments 16 pages, 9 figures, TVCG 2026, project page: https://zx-yin.github.io/dreamlifting/

Journal ref IEEE Transactions on Visualization and Computer Graphics 2026

详情

展开后加载摘要…

URL PDF HTML 收藏