用高斯约束提升无监督场景发现与位姿一致性
Gaussian-Constrained LeJEPA Representations for Unsupervised Scene Discovery and Pose Consistency
- 在LeJEPA基础上施加各向同性高斯约束，优化图像嵌入
- 在IMC2025上实现更优的场景分离与位姿合理性
- 适合研究自监督学习与3D重建融合的学者
从无结构图像集合中进行无监督3D场景重建仍是计算机视觉中的基本挑战，尤其当图像来自多个无关场景且存在显著视觉歧义时。图像匹配挑战2025（IMC2025）在真实条件下要求同时完成场景发现与相机位姿估计，面临异常值和内容混杂问题。本文探讨受LeJEPA启发的高斯约束表示在该任务中的应用。提出三个逐步优化的流程，最终采用一种在学习到的图像嵌入上施加各向同性高斯约束的LeJEPA类方法。不引入新的理论保证，而是实证评估此类约束对聚类一致性和位姿估计鲁棒性的实际影响。在IMC2025上的实验表明，相较于启发式基线，高斯约束嵌入能提升场景分离效果与位姿合理性，尤其在视觉模糊场景中表现更优。结果表明，理论上合理的表示约束为连接自监督学习原理与实际结构-运动管线提供了有前景的方向。
原文摘要 · Abstract (English)
Unsupervised 3D scene reconstruction from unstructured image collections remains a fundamental challenge in computer vision, particularly when images originate from multiple unrelated scenes and contain significant visual ambiguity. The Image Matching Challenge 2025 (IMC2025) highlights these difficulties by requiring both scene discovery and camera pose estimation under real-world conditions, including outliers and mixed content. This paper investigates the application of Gaussian-constrained representations inspired by LeJEPA (Joint Embedding Predictive Architecture) to address these challenges. We present three progressively refined pipelines, culminating in a LeJEPA-inspired approach that enforces isotropic Gaussian constraints on learned image embeddings. Rather than introducing new theoretical guarantees, our work empirically evaluates how these constraints influence clustering consistency and pose estimation robustness in practice. Experimental results on IMC2025 demonstrate that Gaussian-constrained embeddings can improve scene separation and pose plausibility compared to heuristic-driven baselines, particularly in visually ambiguous settings. These findings suggest that theoretically motivated representation constraints offer a promising direction for bridging self-supervised learning principles and practical structure-from-motion pipelines.
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。