研究人员开发了 REVIVE 3D，一种旨在从平面 2D 图像生成详细 3D 资产的新颖两阶段管线。该系统首先通过恢复全局体量并添加部件感知细节来创建“膨胀先验”，然后使用潜在扩散过程来优化此先验。该方法旨在克服当前生成模型在处理来自有限 3D 线索的体量输出时遇到的局限性。该框架还支持图像条件下的 3D 编辑，并引入了新的指标 Compactness 和 Normal Anisotropy 来评估体量和表面质量。 AI
影响 引入了一种从 2D 图像生成详细 3D 资产的新方法，有望改进内容创建管线。
排序理由 这是一篇详细介绍 3D 资产生成新方法的学术论文。
AI 生成摘要 · Google Gemini · 来自 2 个来源。 我们如何撰写摘要 →
arXiv:2604.27504v1 Announce Type: new Abstract: Recent generative models have shown strong performance in generating diverse 3D assets from 2D images, a fundamental research topic in computer vision and graphics. However, these models still struggle to generate voluminous 3D asse…
Recent generative models have shown strong performance in generating diverse 3D assets from 2D images, a fundamental research topic in computer vision and graphics. However, these models still struggle to generate voluminous 3D assets when the input is a flat image that provides …