动态场景重建新方法，提升时序一致性与精度。
Adaptive and Temporally Consistent Gaussian Surfels for Multi-view Dynamic Reconstruction
- 每帧增量优化，自适应融合克隆与分裂策略。
- 跨帧曲率一致，有效减少动态表面抖动。
- 适用于拓扑变化大、运动剧烈的复杂动态场景。
3D Gaussian Splatting 在动态场景的新视角合成和静态场景几何重建中取得显著进展。在此基础上，早期方法通过全局优化整个序列实现动态表面重建，但在面对显著拓扑变化、物体出现或消失以及快速运动的长期序列时仍面临挑战。为此，我们提出 AT-GS，一种基于多视角视频进行高质量动态表面重建的新方法，采用逐帧增量优化。为避免跨帧陷入局部最优，引入统一且自适应的梯度感知稀疏化策略，融合传统克隆与分裂技术的优势；同时，通过保证连续帧间曲率图的一致性，降低动态表面的时序抖动。该方法在空间-时间新视角合成中实现更高的精度与时序连贯性，即使在复杂挑战性场景下也能生成高保真结果。在多个多视角视频数据集上的大量实验验证了其有效性，相较基线方法有明显优势。
原文摘要 · Abstract (English)
3D Gaussian Splatting has recently achieved notable success in novel view synthesis for dynamic scenes and geometry reconstruction in static scenes. Building on these advancements, early methods have been developed for dynamic surface reconstruction by globally optimizing entire sequences. However, reconstructing dynamic scenes with significant topology changes, emerging or disappearing objects, and rapid movements remains a substantial challenge, particularly for long sequences. To address these issues, we propose AT-GS, a novel method for reconstructing high-quality dynamic surfaces from multi-view videos through per-frame incremental optimization. To avoid local minima across frames, we introduce a unified and adaptive gradient-aware densification strategy that integrates the strengths of conventional cloning and splitting techniques. Additionally, we reduce temporal jittering in dynamic surfaces by ensuring consistency in curvature maps across consecutive frames. Our method achieves superior accuracy and temporal coherence in dynamic surface reconstruction, delivering high-fidelity space-time novel view synthesis, even in complex and challenging scenes. Extensive experiments on diverse multi-view video datasets demonstrate the effectiveness of our approach, showing clear advantages over baseline methods. Project page: \url{https://fraunhoferhhi.github.io/AT-GS}
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。