Image-to-3D methods often trade off faithfulness and completeness: depth estimators are anchored to input pixels but stop at the visible surface, while image-to-3D models generate complete shapes that are often misaligned with the input. We introduce World Tracing, a generative pixel-aligned geometry representation that predicts 3D points aligned with observed pixels while completing geometry beyond the visible surface. For each input pixel, World Tracing predicts an ordered stack of camera-space 3D points, where the first layer represents the visible surface and subsequent layers represent front-to-back intersections with occluded surfaces. We instantiate this representation with a world-tracing diffusion transformer, WT-DiT, which treats multiple geometry layers as separate denoising tokens coupled through factorized and global attention. WT-DiT is trained with pixel-space flow matching and a mixed noise schedule that balances visible-surface reconstruction with occluded-geometry generation. World Tracing achieves strong performance on visible-surface reconstruction and complete geometry generation across object, scene, and dynamic benchmarks, outperforming both depth predictors and image-to-3D generators. It also preserves 2D-to-3D correspondence, enabling text-driven 3D scene editing, geometry-conditioned novel-view video synthesis, and training-free integration with textured-mesh generators.

翻译：图像到三维方法常在忠实度与完整性之间权衡：深度估计器锚定输入像素但止步于可见表面，而图像到三维模型虽能生成完整形状却常与输入存在偏差。本文提出世界追踪（World Tracing）——一种生成式像素对齐几何表征，可在预测与观测像素对齐的三维点的同时，补全可见表面之外的几何结构。对于每个输入像素，世界追踪预测一个相机空间三维点有序堆栈，其中首层表征可见表面，后续各层则按从前到后顺序表征被遮挡表面的交点。我们通过世界追踪扩散变换器（WT-DiT）实例化该表征：该模型将多层几何作为独立去噪令牌处理，并通过分解式与全局注意力机制实现耦合。WT-DiT采用像素空间流匹配与混合噪声调度进行训练，在可见表面重建与遮挡几何生成之间取得平衡。在物体、场景及动态基准测试中，世界追踪在可见表面重建与完整几何生成任务上均表现优异，性能超越深度预测器与图像到三维生成器。该方法同时保持了二维到三维的对应关系，支持文本驱动的三维场景编辑、基于几何条件的新视角视频合成，以及与纹理网格生成器的免训练集成。