超越几何：面向沉浸式 2D 转 3D 的艺术化视差合成
Beyond Geometry: Artistic Disparity Synthesis for Immersive 2D-to-3D
把 2D 转 3D 的目标从几何精确的视差估计改为艺术化视差合成，用双路径解耦全局深度参数与局部出屏效果，并借助专业 3D 电影数据做间接监督；对做单目深度、视差估计与立体内容生成的研究者，这提供了一条用电影数据注入艺术意图、而非只追几何精度的新思路。
原文依据 shifting the goal from physically accurate disparity estimation to artistically coherent disparity synthesis
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论当前的 2D 转 3D 方法虽然达到了几何精度，但在艺术性上有所欠缺，无法复现专业 3D 电影那种沉浸式且能引发情感共鸣的体验。这是因为「几何重建」范式把刻意的艺术意图——例如为营造「出屏」效果而有意进行的零平面偏移以及局部深度雕琢——误判为数据「噪声」或歧义。本文主张一种新范式：艺术化视差合成，将目标从物理精确的视差估计转向艺术上连贯的视差合成。我们提出 Art3D，一个探索该范式的初步框架。Art3D 采用双路径架构，将全局深度参数（宏观意图）与局部艺术效果（视觉笔触）解耦，并通过间接监督从专业 3D 电影数据中学习。我们还引入了一种初步的评测方法，用于量化与电影风格的一致性。实验表明，我们的方法在复现关键的局部出屏效果、以及与电影级 3D 内容的全局深度风格对齐方面展现出潜力，为新一代以艺术为驱动的转换工具奠定了基础。
英文原文摘要 1176 字符
Current 2D-to-3D conversion methods achieve geometric accuracy but are artistically deficient, failing to replicate the immersive and emotionally resonant experience of professional 3D cinema. This is because "geometric reconstruction" paradigms mistake deliberate artistic intent--such as strategic zero-plane shifts for "pop-out" effects and local depth sculpting--for data "noise" or ambiguity. This paper argues for a new paradigm: Artistic Disparity Synthesis, shifting the goal from physically accurate disparity estimation to artistically coherent disparity synthesis. We propose Art3D, a preliminary framework exploring this paradigm. Art3D uses a dual-path architecture to decouple global depth parameters (macro-intent) from local artistic effects (visual brushstrokes) and learns from professional 3D film data via indirect supervision. We also introduce a preliminary evaluation method to quantify cinematic alignment. Experiments show our approach demonstrates potential in replicating key local out-of-screen effects and aligning with the global depth styles of cinematic 3D content, laying the groundwork for a new class of artistically-driven conversion tools.