GarmentCrafter: Progressive Novel View Synthesis for Single-View 3D Garment Reconstruction and Editing
This addresses the problem of 3D garment design for non-professional users, representing an incremental improvement over existing single-view reconstruction methods.
The paper tackles the challenge of creating and editing 3D garments from a single-view image for non-professional users, achieving superior visual fidelity and inter-view coherence compared to state-of-the-art methods.
We introduce GarmentCrafter, a new approach that enables non-professional users to create and modify 3D garments from a single-view image. While recent advances in image generation have facilitated 2D garment design, creating and editing 3D garments remains challenging for non-professional users. Existing methods for single-view 3D reconstruction often rely on pre-trained generative models to synthesize novel views conditioning on the reference image and camera pose, yet they lack cross-view consistency, failing to capture the internal relationships across different views. In this paper, we tackle this challenge through progressive depth prediction and image warping to approximate novel views. Subsequently, we train a multi-view diffusion model to complete occluded and unknown clothing regions, informed by the evolving camera pose. By jointly inferring RGB and depth, GarmentCrafter enforces inter-view coherence and reconstructs precise geometries and fine details. Extensive experiments demonstrate that our method achieves superior visual fidelity and inter-view coherence compared to state-of-the-art single-view 3D garment reconstruction methods.