REVIVE 3D：通过编码膨胀先验细化实现体积增强
REVIVE 3D: Refinement via Encoded Voluminous Inflated prior for Volume Enhancement
针对单张平面图像 3D 线索不足的问题，先用前景轮廓膨胀构造 Inflated Prior 恢复全局体积，再在 3D 潜变量上加噪去噪、借预训练骨干的 3D 先验细化几何；这套「先构造粗体积先验再潜空间细化」的两阶段即插即用思路，可直接迁移到单图/稀疏视角三维生成与编辑任务。
原文依据 3D Latent Refinement injects Gaussian noise into the Inflated Prior's latent and then denoises it
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论近期生成模型在从二维图像生成多样化三维资产方面表现强劲，这是计算机视觉与图形学中的基础研究课题。然而，当输入是仅提供有限三维线索的平面图像时，这些模型仍难以生成具有体积感的三维资产。我们提出 REVIVE 3D，一个从平面图像生成具有体积感三维资产的两阶段、即插即用流程。在第一阶段，我们通过膨胀前景轮廓以恢复全局体积，并叠加部件感知细节以捕捉局部结构，从而构造出膨胀先验。在第二阶段，三维潜变量细化向膨胀先验的潜变量注入高斯噪声再对其去噪，利用该先验的几何线索调用骨干网络预训练的三维知识。此外，我们的框架支持以图像为条件的三维编辑。为量化体积感与表面平坦程度，我们提出紧凑度与法向各向异性两项指标。我们通过用户研究验证了紧凑度与法向各向异性，表明这些指标与人类对体积和质量的感知相一致。基于大量定性与定量评估，我们展示 REVIVE 3D 在一个具有挑战性的平面图像数据集上取得了最优性能。
英文原文摘要 1235 字符
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 limited 3D cues. We introduce REVIVE 3D, a two-stage, plugand-play pipeline for generating voluminous 3D assets from flat images. In Stage 1, we construct an Inflated Prior by inflating the foreground silhouette to recover global volume and superimposing part-aware details to capture local structure. In Stage 2, 3D Latent Refinement injects Gaussian noise into the Inflated Prior's latent and then denoises it, using the prior's geometric cues to leverage the backbone's pretrained 3D knowledge. Furthermore, our framework supports image-conditioned 3D editing. To quantify volume and surface flatness, we propose Compactness and Normal Anisotropy. We validate Compactness and Normal Anisotropy through a user study, showing that these metrics align with human perception of volume and quality. We show that REVIVE 3D achieves state-of-the-art performance on a challenging flat image dataset, based on extensive qualitative and quantitative evaluations.