用单张图片直接补全点云，迭代优化细节，性能领先。
I2PRef: Image-Driven Point Completion with Iterative Refinement
- 以图像为几何主源，直接生成完整点云，无需3D输入。
- 迭代式精修模块提升细节，相比之前方法减少12.3%的差值距离。
- 适合需要高质量点云重建的视觉与三维建模研究者。
我们提出一种图像驱动的点云补全方法，将图像作为主要几何信息来源而非辅助引导。为此，引入图像到点云（I2P）模块，可仅凭单张RGB图像直接重建完整点云，无需任何3D输入。此外，设计基于Transformer的点到点（P2P）精修模块，利用点特征与图像特征间的自注意力和交叉注意力，对粗略的I2P输出进行迭代优化。I2P模块使图像编码器学习丰富的几何表征，而P2P模块逐步恢复细粒度细节。与依赖额外损失或融合模块的现有多模态方法不同，我们提出的显式I2P任务仅基于图像就提供了强而有效的几何先验。在ShapeNet-ViPC数据集上的大量实验表明，该方法达到当前最优完成性能，相较之前方法在Chamfer Distance上相对提升12.3%。代码已开源：https://github.com/AzharSindhi/I2PRef.git
原文摘要 · Abstract (English)
We present an image-conditioned point cloud completion approach that treats images as the primary geometric source rather than a secondary guide. To this end, we introduce an Image-to-Point (I2P) module that can reconstruct complete point clouds directly from a single RGB image, with no need for 3D inputs. Additionally, we introduce a transformer-based Point-to-Point (P2P) refinement module that uses self- and cross-attention between point tokens and image features to iteratively refine the coarse I2P output. The I2P module enables the image encoder to learn rich geometric representations, while the P2P module progressively recovers fine-grained details. Unlike existing multimodal methods that rely on auxiliary losses or fusion modules, our explicit I2P task provides a strong, geometry-aware prior based on images alone. Extensive experiments on ShapeNet-ViPC demonstrate state-of-the-art completion performance with a 12.3% relative Chamfer Distance improvement over prior methods. Code is available at: https://github.com/AzharSindhi/I2PRef.git
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。