ObjFiller-3D：基於視頻擴散模型的多視角3D修復一致性方法

ObjFiller-3D: Consistent Multi-view 3D Inpainting via Video Diffusion Models

August 25, 2025

作者: Haitang Feng, Jie Liu, Jie Tang, Gangshan Wu, Beiqi Chen, Jianhuang Lai, Guangcong Wang

cs.AI

摘要

三維修復通常依賴於多視角二維圖像修復，然而不同修復視圖之間固有的不一致性可能導致紋理模糊、空間不連續以及視覺偽影等問題。這些不一致性在追求精確且逼真的三維物體補全時，尤其是在要求高保真度和結構連貫性的應用中，構成了重大挑戰。為克服這些限制，我們提出了ObjFiller-3D，一種專為高質量且一致的三維物體補全與編輯而設計的新方法。與傳統的二維圖像修復模型不同，我們的方法利用精選的頂尖視頻編輯模型來填充三維物體的遮罩區域。我們分析了三維與視頻之間的表示差距，並提出了一種適用於三維場景修復的視頻修復模型改進方案。此外，我們引入了一種基於參考的三維修復方法，以進一步提升重建質量。多樣化數據集上的實驗表明，與先前方法相比，ObjFiller-3D產生了更為忠實且細緻的重建結果（PSNR為26.6對比NeRFiller的15.9，LPIPS為0.19對比Instant3dit的0.25）。此外，它展現了在實際三維編輯應用中部署的強大潛力。項目頁面：https://objfiller3d.github.io/ 代碼：https://github.com/objfiller3d/ObjFiller-3D。

English

3D inpainting often relies on multi-view 2D image inpainting, where the inherent inconsistencies across different inpainted views can result in blurred textures, spatial discontinuities, and distracting visual artifacts. These inconsistencies pose significant challenges when striving for accurate and realistic 3D object completion, particularly in applications that demand high fidelity and structural coherence. To overcome these limitations, we propose ObjFiller-3D, a novel method designed for the completion and editing of high-quality and consistent 3D objects. Instead of employing a conventional 2D image inpainting model, our approach leverages a curated selection of state-of-the-art video editing model to fill in the masked regions of 3D objects. We analyze the representation gap between 3D and videos, and propose an adaptation of a video inpainting model for 3D scene inpainting. In addition, we introduce a reference-based 3D inpainting method to further enhance the quality of reconstruction. Experiments across diverse datasets show that compared to previous methods, ObjFiller-3D produces more faithful and fine-grained reconstructions (PSNR of 26.6 vs. NeRFiller (15.9) and LPIPS of 0.19 vs. Instant3dit (0.25)). Moreover, it demonstrates strong potential for practical deployment in real-world 3D editing applications. Project page: https://objfiller3d.github.io/ Code: https://github.com/objfiller3d/ObjFiller-3D .