用语义信息提升稀疏视角3D重建精度，显著减少模糊与误差。
SERES: Semantic-aware neural reconstruction from sparse views
- 引入基于图像块的语义逻辑值，联合优化距离场与辐射场。
- 在DTU数据集上使SparseNeuS误差降44%，VolRecon降20%。
- 可作为插件适配主流重建模型，效果提升超60%。
我们提出一种语义感知的神经重建方法，从稀疏图像生成高保真3D模型。为解决稀疏输入导致的辐射度歧义问题，我们在神经隐式表示中引入可优化的基于图像块的语义逻辑值，与符号距离场和辐射场共同优化。提出一种基于几何原始体掩码的新正则化方法，以缓解形状歧义。实验验证表明，本方法在DTU数据集上的平均Chamfer距离相比SparseNeuS降低44%，相比VolRecon降低20%。作为插件应用于NeuS和Neuralangelo等密集重建基线时，平均误差分别降低69%和68%。
原文摘要 · Abstract (English)
We propose a semantic-aware neural reconstruction method to generate 3D high-fidelity models from sparse images. To tackle the challenge of severe radiance ambiguity caused by mismatched features in sparse input, we enrich neural implicit representations by adding patch-based semantic logits that are optimized together with the signed distance field and the radiance field. A novel regularization based on the geometric primitive masks is introduced to mitigate shape ambiguity. The performance of our approach has been verified in experimental evaluation. The average chamfer distances of our reconstruction on the DTU dataset can be reduced by 44% for SparseNeuS and 20% for VolRecon. When working as a plugin for those dense reconstruction baselines such as NeuS and Neuralangelo, the average error on the DTU dataset can be reduced by 69% and 68% respectively.
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。