Test-Time Baking (TTB) 发布：用于高效渲染解码器仅大视图合成模型的策略
TTB: Test-time Baking for Efficient Rendering of Decoder-only View Synthesis Models
Test-Time Baking (TTB) 策略通过将交叉视图注意力中的全局场景信息烘焙到轻量级 MLP，在保持 Test-Time Training 效率的同时提升了大视图合成模型（LVSMs）新视角解码的保真度，在多个基准测试中实现了高达 23 倍的渲染速度提升且质量与当前最优技术相当。
Published on Nov 12
Authors:
,
,
,
,
,
,
Abstract
By baking global scene information from cross-view attention into a lightweight MLP, Test-Time Baking (TTB) enhances the fidelity of novel-view decoding in Large View Synthesis Models while maintaining the efficiency of Test-Time Training.
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
View arXiv page View PDF Project page GitHub 32 Add to collection
Get this paper in your agent:
hf papers read 2611.17331
Don't have the latest CLI?
curl -LsSf https://hf.co/cli/install.sh | bash
Models citing this paper 0
No model linking this paper
Cite arxiv.org/abs/2611.17331 in a model README.md to link it from this page.
Datasets citing this paper 0
No dataset linking this paper
Cite arxiv.org/abs/2611.17331 in a dataset README.md to link it from this page.
Spaces citing this paper 1
Collections including this paper 0
No Collection including this paper
Add this paper to a collection to link it from this page.
来源: Hugging Face Daily Papers · huggingface.co