SceneTex：基于扩散先验的高质量室内场景纹理合成
SceneTex: High-Quality Texture Synthesis for Indoor Scenes via Diffusion Priors
AI总结：
SceneTex提出一种基于深度到图像扩散先验的室内场景纹理合成方法，通过多分辨率纹理场和交叉注意力解码器在RGB空间中优化生成高质量且风格一致的纹理，在3D-FRONT场景上显著优于已有方法。
摘要：
我们提出SceneTex，一种利用深度到图像扩散先验为室内场景有效生成高质量且风格一致纹理的新方法。与以往要么将2D视图迭代地扭曲到网格表面、要么在没有精确几何和风格线索的情况下蒸馏扩散潜在特征的方法不同，SceneTex将纹理合成任务表述为RGB空间中的优化问题，在该空间中风格和几何一致性得到恰当反映。其核心是SceneTex提出了一种多分辨率纹理场来隐式编码网格外观。我们通过基于分数蒸馏的目标函数在相应的RGB渲染中优化目标纹理。为了进一步确保跨视图的风格一致性，我们引入了一个交叉注意力解码器，通过对每个实例中预先采样的参考位置进行交叉注意力来预测RGB值。SceneTex能够为3D-FRONT场景实现多样且精确的纹理合成，在视觉质量和提示保真度方面相比先前的纹理生成方法展现出显著改进。
英文摘要：
We propose SceneTex, a novel method for effectively generating high-quality and style-consistent textures for indoor scenes using depth-to-image diffusion priors. Unlike previous methods that either iteratively warp 2D views onto a mesh surface or distillate diffusion latent features without accurate geometric and style cues, SceneTex formulates the texture synthesis task as an optimization problem in the RGB space where style and geometry consistency are properly reflected. At its core, SceneTex proposes a multiresolution texture field to implicitly encode the mesh appearance. We optimize the target texture via a score-distillation-based objective function in respective RGB renderings. To further secure the style consistency across views, we introduce a cross-attention decoder to predict the RGB values by cross-attending to the pre-sampled reference locations in each instance. SceneTex enables various and accurate texture synthesis for 3D-FRONT scenes, demonstrating significant improvements in visual quality and prompt fidelity over the prior texture generation methods.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
