本文介绍一下我们在 ICCV 2025 上的新工作： 这篇文章针对 Image-to-3D 生成任务设计了一种全新的 pixel-level 的 3D Diffusion，名为 DiffusionGS。通过在 Diffusion 的每一个 timestep 都预测一个 3D Gaussian 点云来保持生成结果的视角一致性（3D view consistancy），不仅能够用于 object-centric 的物体生成，还能够用于 larger-scale 的 scene-level 场景 生成。 Object 生成效果： 图1. object-centric 3D 生成效果展示 Scene 重建效果： 点击下方 卡片 ，关注" 3D视觉之心 "公众号 第一时间获取 3D视觉干货 图2. Single-view Scene-level 重建效果展示 目前 training, testing, evaluation 的代码已经开源，为方便大家使用，还集成了一行 pipeline 直接运行的代码。代码晚点会包括高斯点云转 mesh。比如下图 3 中的 ikun 玩偶和死侍玩偶： 欢迎大家来使用、提 issue、交 ...

Core Viewpoint - The article emphasizes the advancements in autonomous driving scene reconstruction, highlighting the integration of various technologies and the collaboration among top universities and research institutions in this field [2][12]. Summary by Sections Section 1: Overview of Autonomous Driving Scene Reconstruction - The article discusses the importance of dynamic and static scene reconstruction in autonomous driving, focusing on the need for precise color and geometric information through the integration of lidar and visual data [2]. Section 2: Research Contributions - Several notable research works from prestigious institutions such as Tsinghua University, Nankai University, Fudan University, and the University of Illinois Urbana-Champaign are mentioned, showcasing their contributions to the field [5][6][10][11]. Section 3: Educational Initiatives - The article promotes a comprehensive course on 3D Gaussian Splatting (3DGS), designed in collaboration with leading experts, aimed at providing in-depth knowledge and practical skills in autonomous driving scene reconstruction [15][19]. Section 4: Course Structure - The course is structured into eight chapters, covering foundational algorithms, technical details of 3DGS, static and dynamic scene reconstruction, surface reconstruction, and practical applications in autonomous driving [19][21][23][25][27][29][31][33]. Section 5: Target Audience - The course is targeted at researchers, students, and professionals interested in 3D reconstruction, requiring a foundational understanding of 3DGS and related technologies [36][37].