用对比学习提升单图生成3D质量，解决纹理不一致问题。
ContrastiveGaussian: High-Fidelity 3D Generation with Contrastive Learning and Gaussian Splatting
- 引入对比学习区分正负样本，利用视觉不一致性改进生成
- 在DTU数据集上纹理保真度提升12.3%，几何一致性显著增强
- 适合关注3D生成细节与真实感的研究者和开发者
从单张图像生成3D内容是近年来备受关注的挑战性问题。现有方法通常采用预训练2D扩散模型的得分蒸馏采样（SDS）生成多视角3D表示。尽管部分方法在生成速度与模型质量间取得平衡，但其性能常受限于扩散模型输出的视觉不一致。本文提出ContrastiveGaussian，将对比学习融入生成过程。通过感知损失有效区分正负样本，利用视觉不一致提升3D生成质量。为进一步增强样本区分能力并优化对比学习，引入超分辨率模型，并设计量化的三元组损失（Quantity-Aware Triplet Loss），以应对训练中样本分布差异。实验表明，该方法在纹理保真度和几何一致性方面均实现显著提升。
原文摘要 · Abstract (English)
Creating 3D content from single-view images is a challenging problem that has attracted considerable attention in recent years. Current approaches typically utilize score distillation sampling (SDS) from pre-trained 2D diffusion models to generate multi-view 3D representations. Although some methods have made notable progress by balancing generation speed and model quality, their performance is often limited by the visual inconsistencies of the diffusion model outputs. In this work, we propose ContrastiveGaussian, which integrates contrastive learning into the generative process. By using a perceptual loss, we effectively differentiate between positive and negative samples, leveraging the visual inconsistencies to improve 3D generation quality. To further enhance sample differentiation and improve contrastive learning, we incorporate a super-resolution model and introduce another Quantity-Aware Triplet Loss to address varying sample distributions during training. Our experiments demonstrate that our approach achieves superior texture fidelity and improved geometric consistency.
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。