Optimal texture map reconstruction from multiple views
Optimal texture map reconstruction from multiple views
复制标题
DOI：
10.1109/cvpr.2001.990496
复制
发表时间：
2001-12
期刊：
影响因子：
--
通讯作者：
Lifeng Wang;S. B. Kang;R. Szeliski;H. Shum
中科院分区：
文献类型：
--
作者：
Lifeng Wang;S. B. Kang;R. Szeliski;H. Shum
从多个参考图像中恢复 3D 模型不仅涉及 3D 形状的提取，还涉及纹理的提取。假设所有表面都是朗伯表面，所得的最终纹理通常被计算为参考纹理的线性组合。然而，这不是重建纹理的最佳方法，因为这不会对纹理投影中的各向异性进行建模。此外，空间图像采样在缩短的表面内可能变化很大。这对于涉及合成分析的计算机视觉技术以及依赖于视图的纹理映射 (VDTM) 的基于图像的渲染 (IBR) 技术也具有重要意义。从采样理论开始，我们展示了权重应如何在空间上分布以实现最佳纹理构造。局部权重考虑了各向异性和可变空间图像采样的影响。我们还提供了实验结果来验证我们的分析。
The recovery of 3D models from multiple reference images involves not only the extraction of 3D shape, but also of texture. Assuming that all surfaces are Lambertian, the resulting final texture is typically computed as a linear combination of reference textures. This is, however, not the optimal means for reconstructing textures, since this does not model the anisotropy in the texture projection. Furthermore, the spatial image sampling may be quite variable within a fore-shortened surface. This also has important implications for computer vision techniques that involve analysis by synthesis and the image-based rendering (IBR) technique of view-dependent texture mapping (VDTM). Starting with sampling theory, we show how weights should be spatially distributed for optimal texture construction. The local weights take into consideration the effects of anisotropy and variable spatial image sampling. We also present experimental results to verify our analysis.