Repaint123：快速且高品質的一圖到3D生成，具有漸進可控的2D複製。

摘要

最近常見的一種將單張圖像轉換為3D的方法通常採用得分蒸餾取樣（SDS）。儘管取得了令人印象深刻的結果，但存在著多個缺陷，包括多視圖不一致、過飽和和過平滑的紋理，以及生成速度緩慢等問題。為了解決這些缺陷，我們提出了Repaint123，以減輕多視圖偏差、紋理降解並加快生成過程。其核心思想是結合2D擴散模型的強大圖像生成能力和重新繪製策略的紋理對齊能力，生成具有一致性的高質量多視圖圖像。我們進一步提出了可視性感知自適應重新繪製強度，用於增強重新繪製過程中重疊區域的生成圖像質量。生成的高質量和多視圖一致的圖像使得可以使用簡單的均方誤差（MSE）損失進行快速3D內容生成。我們進行了大量實驗，並展示了我們的方法在2分鐘內從頭開始生成具有高質量、多視圖一致性和精細紋理的3D內容的卓越能力。代碼位於https://github.com/junwuzhang19/repaint123。

English

Recent one image to 3D generation methods commonly adopt Score Distillation Sampling (SDS). Despite the impressive results, there are multiple deficiencies including multi-view inconsistency, over-saturated and over-smoothed textures, as well as the slow generation speed. To address these deficiencies, we present Repaint123 to alleviate multi-view bias as well as texture degradation and speed up the generation process. The core idea is to combine the powerful image generation capability of the 2D diffusion model and the texture alignment ability of the repainting strategy for generating high-quality multi-view images with consistency. We further propose visibility-aware adaptive repainting strength for overlap regions to enhance the generated image quality in the repainting process. The generated high-quality and multi-view consistent images enable the use of simple Mean Square Error (MSE) loss for fast 3D content generation. We conduct extensive experiments and show that our method has a superior ability to generate high-quality 3D content with multi-view consistency and fine textures in 2 minutes from scratch. Code is at https://github.com/junwuzhang19/repaint123.

Repaint123：快速且高品質的一圖到3D生成，具有漸進可控的2D複製。

Repaint123: Fast and High-quality One Image to 3D Generation with Progressive Controllable 2D Repainting

摘要

Support