用可追踪的物体锚点，让长视频3D重建更连贯准确
LIST3R: Long-sequence Instance-aware 3D Reconstruction
- 以物体为锚点组织长序列重建，保持对象一致性
- 在多个片段间匹配锚点，修复重访区域并提升对齐精度
- 适合长时序3D场景重建，尤其动态变化大的环境
我们提出LIST3R，一种受人类空间记忆机制启发的实例感知长序列3D重建框架。该方法围绕稳定可识别的实例锚点组织重建过程，利用这些锚点连接断裂的子序列，并将局部观测融合为一致的全局3D场景。给定一段长视频，算法将其划分为重叠子序列，为每个局部重建构建结构化的实例库，通过语义与几何证据维持可追踪的锚点。跨子序列匹配锚点以恢复重访区域，并提供对象感知约束用于片段对齐，实现一致的全局重建。在此过程中，不断更新的几何证据逐步将局部实例库整合为统一的全局3D实例库。在多个长序列基准测试上，本方法生成了更精确的轨迹和更高质量的3D重建，验证了持久实例锚点在长时域重建中的有效性。代码已公开于项目主页：https://yixn965.github.io/LIST3R/
原文摘要 · Abstract (English)
We present LIST3R, an instance-aware framework for long-sequence 3D reconstruction inspired by the way humans organize spatial memory around stable and recognizable objects. LIST3R organizes long-sequence reconstruction around instance anchors, using them to reconnect fragmented subsequences and consolidate local observations into a coherent global 3D scene. Given a long video, our approach partitions it into overlapping subsequences and builds a structured local instance library for each partial reconstruction, maintaining persistent trackable anchors with semantic and geometric evidence. These anchors are matched across subsequences to recover revisited regions and provide object-aware constraints for fragment alignment, producing a consistent global reconstruction. During this process, the evolving geometric evidence updates the local instance libraries and progressively organizes them into a unified global 3D instance library. Experiments on long-sequence benchmarks show that our method produces more accurate trajectories and higher-quality 3D reconstructions, highlighting the effectiveness of persistent instance anchors for organizing long-horizon 3D reconstruction. Our code is available on the project page: https://yixn965.github.io/LIST3R/.
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。