Paper Detail

TTB: Test-time Baking for Efficient Rendering of Decoder-only View Synthesis Models

Chin-Yang Lin, Ryo Hachiuma, Jaesung Choe, Min-Hung Chen, Yu-Chiang Frank Wang, Yen-Yu Lin, Wei-Chen Chiu, Yu-Lun Liu, Cheng Sun

arxiv Score 5.8

Published 2026-11-12 · First seen 2026-11-13

General AI

Abstract

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

Workflow Status

Review status
pending
Role
unreviewed
Read priority
later
Vote
Not set.
Saved
no
Collections
Not filed yet.
Next action
Not filled yet.

Reading Brief

No structured notes yet. Add `summary_sections`, `why_relevant`, `claim_impact`, or `next_action` in `papers.jsonl` to enrich this view.

Why It Surfaced

No ranking explanation is available yet.

Tags

No tags.

BibTeX

@article{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},
  abstract = {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 },
  url = {https://arxiv.org/abs/2611.17331},
  keywords = {cs.CV, Decoder-only Large View Synthesis Models (LVSMs), KV-cache, Novel views, Test-Time Training (TTT), Test-Time Baking (TTB), Cross-view attention, Lightweight MLP, Context prefilling, Modality misalignment, Context tokens, Context ground-truth tokens, code available, huggingface daily},
  eprint = {2611.17331},
  archiveprefix = {arXiv},
}

Metadata

{}