TTB：用于高效渲染仅解码器视图合成模型的测试时烘焙
TTB: Test-time Baking for Efficient Rendering of Decoder-only View Synthesis Models
AI总结：
针对仅解码器视图合成模型渲染效率与质量的矛盾，提出TTB策略，通过复用TTT的MLP并解耦上下文标记，实现23倍渲染加速且质量达最先进水平。
摘要：
带有KV缓存的仅解码器大型视图合成模型（LVSMs）近期通过从神经网络回归新视图、无需重建3D几何实现了最先进的质量，而测试时训练（TTT）层虽节省计算量却牺牲了质量。我们提出测试时烘焙（TTB）策略，该策略学习将跨视图注意力的全局场景信息烘焙到轻量级MLP中，实现快速且高保真的新视图解码。第一个关键是重新利用TTT的快速权重MLP，从其输入输出对中显式学习跨视图注意力映射，而非完全替换注意力，达到与TTT相同的渲染效率，同时提供显著更高的质量。第二个关键解决上下文预填充与新视图渲染之间的模态失配问题：我们将上下文标记解耦为仅相机的上下文渲染标记（作为TTB输入）和带有图像内容的上下文真值标记（作为TTB映射目标），确保烘焙后的MLP摆脱上下文与新视图处理之间的模态泛化挑战。我们的方法在多个基准上实现了高达23倍的渲染加速，质量与最先进水平相当。项目页面：this https URL
英文摘要：
Decoder-only Large View Synthesis Models (LVSMs) with KV-cache have recently achieved state-of-the-art quality by regressing novel views from neural networks without reconstructing 3D geometry, while Test-Time Training (TTT) layers save computation but sacrifice quality. We propose Test-Time Baking (TTB), a strategy that learns to bake global scene information from cross-view attention into a lightweight MLP, enabling fast and high-fidelity novel-view decoding. The first key is to repurpose the fast-weight MLP of TTT to learn the cross-view attention mapping explicitly from its input-output pairs, rather than replacing attention entirely, achieving the same rendering efficiency as TTT while delivering substantially higher quality. The second key addresses a modality misalignment between context prefilling and novel-view rendering: we disentangle context tokens into camera-only context rendering tokens to serve as TTB input, and context ground-truth tokens with image content to serve as the TTB mapping target, ensuring the baked MLPs are relieved of the modality generalization challenge between context and novel-view processing. Our method achieves up to **23x** rendering speedup with quality on par with the state-of-the-art across several benchmarks. Project page: https://test-time-baking.github.io
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。
