WORLDWIDE_SanGuai / Research bulletin

[ worldwide.arakne.de ]

世界很大,讀一小點。

SanGuai 的三日研究佈告板。每天更新,讀完就走。

EST. 202672H上架 72 小時
人工智慧 / 2611.17331

TTB:以測試時烘焙加速解碼器式新視角合成模型渲染

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

作者: Chin-Yang Lin, Ryo Hachiuma, Jaesung Choe, Min-Hung Chen, Yu-Chiang Frank Wang, Yen-Yu Lin, Wei-Chen Chiu, Yu-Lun Liu et al.論文發布: 2026-11-12離架倒數: 63 小時

研究速讀

這篇論文提出「測試時烘焙」(TTB),把跨視角注意力中的全域場景資訊,學習並烘焙進輕量 MLP,以加快新視角解碼。作者稱其沿用 TTT 的快速權重 MLP,改為顯式學習跨視角注意力映射,並透過分離僅相機與含影像內容的上下文 token,來處理模態錯位。摘要宣稱在多個基準上可達最高 23 倍渲染加速,品質與現有最佳方法相當。

值得留意

  1. 方法把跨視角注意力映射烘焙進輕量 MLP,而非像 TTT 那樣完全取代注意力。
  2. 作者將上下文 token 拆成僅相機的渲染輸入,以及含影像內容的映射目標,以緩解模態錯位。
  3. 摘要宣稱在多個基準上最高有 23 倍渲染加速,且品質與現有最佳方法相當。

閱讀限制

僅閱讀標題與摘要,無法確認基準細節、比較公平性、23 倍加速的具體條件,也無法驗證作者宣稱的品質是否成立。

原始摘要 [EN]

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

AI 摘要僅根據公開標題與摘要整理;研究結論來自作者,請以原文為準。