titleTTB: Test-time Baking for Efficient Rendering of Decoder-only View Synthesis Models
authorsChin-Yang Lin, Ryo Hachiuma, Jaesung Choe, Min-Hung Chen, Yu-Chiang Frank Wang, Yen-Yu Lin, Wei-Chen Chiu, Yu-Lun Liu, Cheng Sun
date2026-11-12
venuearXiv (preprint, not peer reviewed)
idarXiv:2611.17331
affiliationNVIDIA
upvotes22 (Hugging Face Daily Papers, 2026-11-15)
linksabs pdf hf code
cite
relatedCosmos 3: Omnimodal World Models for Physical AI
LocateAnything: Fast and High-Quality Vision-Language Grounding with Parallel Box Decoding
LongLive-2.0: An NVFP4 Parallel Infrastructure for Long Video Generation
SpatialClaw: Rethinking Action Interface for Agentic Spatial Reasoning
SoL-Pi: Recursively Scaling Auto-Research Loops for Efficient Agent Harness
abstractDecoder-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

bibtex

@misc{lin2026ttb,
  title={TTB: Test-time Baking for Efficient Rendering of Decoder-only View Synthesis Models},
  author={Chin-Yang Lin and Ryo Hachiuma and Jaesung Choe and Min-Hung Chen and Yu-Chiang Frank Wang and Yen-Yu Lin and Wei-Chen Chiu and Yu-Lun Liu and Cheng Sun},
  year={2026},
  eprint={2611.17331},
  archivePrefix={arXiv},
  url={https://arxiv.org/abs/2611.17331}
}