AToM：使用2D擴散的攤銷式文本轉網格

摘要

我們介紹了分期攤銷文本轉網格（AToM），這是一種優化的前饋式文本轉網格框架，可同時應用於多個文本提示。與現有的文本轉3D方法相比，這些方法通常需要耗時的每個提示的優化，並且通常輸出的表示形式不是多邊形網格，AToM在不到1秒的時間內直接生成高質量的帶紋理網格，訓練成本降低約10倍，並且具有泛化到未見提示的能力。我們的關鍵思想是一種基於新穎的三平面文本轉網格架構，採用兩階段攤銷優化策略，確保穩定的訓練並實現可擴展性。通過在各種提示基準上進行大量實驗，AToM在DF415數據集中的準確性顯著優於最先進的攤銷方法，達到超過4倍的準確性，並產生更具區分性和高質量的3D輸出。AToM展示了強大的泛化能力，為未見的插值提示提供細緻的3D資產，而無需在推斷期間進行進一步優化，這與每個提示的解決方案不同。

English

We introduce Amortized Text-to-Mesh (AToM), a feed-forward text-to-mesh framework optimized across multiple text prompts simultaneously. In contrast to existing text-to-3D methods that often entail time-consuming per-prompt optimization and commonly output representations other than polygonal meshes, AToM directly generates high-quality textured meshes in less than 1 second with around 10 times reduction in the training cost, and generalizes to unseen prompts. Our key idea is a novel triplane-based text-to-mesh architecture with a two-stage amortized optimization strategy that ensures stable training and enables scalability. Through extensive experiments on various prompt benchmarks, AToM significantly outperforms state-of-the-art amortized approaches with over 4 times higher accuracy (in DF415 dataset) and produces more distinguishable and higher-quality 3D outputs. AToM demonstrates strong generalizability, offering finegrained 3D assets for unseen interpolated prompts without further optimization during inference, unlike per-prompt solutions.

AToM：使用2D擴散的攤銷式文本轉網格

AToM: Amortized Text-to-Mesh using 2D Diffusion

摘要

Support