SIFU: Side-view Conditioned Implicit Function for Real-world Usable Clothed Human Reconstruction

Zechuan Zhang, Zongxin Yang*, Yi Yang
ReLER, CCAI, Zhejiang University
CVPR 2024 Highlight
*Corresponding Author
Paper Code arXiv

With just a single image, SIFU is capable of reconstructing a high-quality 3D clothed human model, making it well-suited for practical applications such as scene creation and 3D printing.

Abstract

Creating high-quality 3D models of clothed humans from single images for real-world applications is crucial. Despite recent advancements, accurately reconstructing humans in complex poses or with loose clothing from in-the-wild images, along with predicting textures for unseen areas, remains a significant challenge. A key limitation of previous methods is their insufficient prior guidance in transitioning from 2D to 3D and in texture prediction. In response, we introduce SIFU (Side-view Conditioned Implicit Function for Real-world Usable Clothed Human Reconstruction), a novel approach combining a Side-view Decoupling Transformer with a 3D Consistent Texture Refinement pipeline. SIFU employs a cross-attention mechanism within the transformer, using SMPL-X normals as queries to effectively decouple side-view features in the process of mapping 2D features to 3D. This method not only improves the precision of the 3D models but also their robustness, especially when SMPL-X estimates are not perfect. Our texture refinement process leverages text-to-image diffusion-based prior to generate realistic and consistent textures for invisible views. Through extensive experiments, SIFU surpasses SOTA methods in both geometry and texture reconstruction, showcasing enhanced robustness in complex scenarios and achieving an unprecedented Chamfer and P2S measurement. Our approach extends to practical applications such as 3D printing and scene building, demonstrating its broad utility in real-world scenarios.

teaser

Given a single image, SIFU constructs a 3D clothed human mesh with coarse textures using a Side-view Conditioned Implicit Function. This is followed by a step of 3D Consistent Texture Refinement to generate detailed textures. Specifically, SIFU employs a side-view decoupling transformer to decouple features from the input image and the side-view normals of the SMPL-X model. Then, these features are combined at a query point through a hybrid prior fusion strategy, aiding in the reconstruction of both the mesh and its texture. Finally, the mesh with its basic textures undergoes a diffusion-based 3D consistent texture refinement, ensuring feature consistency in the latent space and resulting in high-quality textures. Please see the paper for more details.

teaser

Texture Editing

动画展示

Animation with Mixamo and Blender.

teaser

Building Scenes with SIFU

BibTeX

@InProceedings{Zhang_2024_CVPR,
        author    = {Zhang, Zechuan and Yang, Zongxin and Yang, Yi},
        title     = {SIFU: Side-view Conditioned Implicit Function for Real-world Usable Clothed Human Reconstruction},
        booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
        month     = {June},
        year      = {2024},
        pages     = {9936-9947}
    }