ObjFiller-3D: Consistent Multi-view 3D Inpainting via Video Diffusion Models
By: Haitang Feng , Jie Liu , Jie Tang and more
Potential Business Impact:
Fixes 3D objects by using video tricks.
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 .
Similar Papers
Perspective-aware 3D Gaussian Inpainting with Multi-view Consistency
CV and Pattern Recognition
Fixes 3D pictures so they look real from all sides.
GaussVideoDreamer: 3D Scene Generation with Video Diffusion and Inconsistency-Aware Gaussian Splatting
CV and Pattern Recognition
Makes 3D worlds from videos, faster and better.
View-Consistent Diffusion Representations for 3D-Consistent Video Generation
CV and Pattern Recognition
Makes computer-made videos look more real.