Newest papers

Stream4D: Streaming 4D Reconstruction with Training-free Motion Decoupling via Causal KV-Cache Attention

Wei Zhang, Ying Feng, Mengtong Wu, Shiqiang Gong, Huaqi Zhang, Qi Zhang · 2026 · arXiv (Cornell University)

DOI: 10.48550/arxiv.2610.31320 · cited by 0 works (OpenAlex) · open-access PDF

Korean

4D 장면 재구성은 역동적 인 개체에 대한 강력한 처리가 필요하지만 기존 스트리밍 방법은 일반적으로 정적 장면을 가정하여 긴 시퀀스에 걸쳐 포즈 드리프 및 유령 유물을 가져옵니다. 우리는 Stream4D를 소개합니다. 훈련이없는, 움직임을 해제한 스트리밍 재구성 프레임 워크는 원인 변환기 척추 (예를 들어, StreamVGGT, Stream3R)에 직접 통합 할 수 있습니다. 우리의 주요 관찰은 원인주의가 암호적으로 KV 캐시 내에서 풍부한 시간 운동 퀴즈를 인코딩한다는 것입니다. 우리는 적응적으로 여러 관심 계층과 시간 창문을 통해 이러한 퀴즈를 집계하고 깊이 프리어와 결합하여 도전적인 사

Machine translation (Meta M2M100); the English original follows.

Abstract

4D scene reconstruction requires robust handling of dynamic objects, yet existing streaming methods commonly assume static scenes, leading to pose drift and ghosting artifacts over long sequences. We introduce Stream4D, a training-free, motion-decoupled streaming reconstruction framework that can be directly integrated into causal Transformer backbones (e.g., StreamVGGT, Stream3R). Our key observation is that causal attention implicitly encodes rich temporal motion cues within the KV cache. We adaptively aggregate these cues from multiple attention layers and across temporal windows, and fuse them with depth priors to handle challenging cases such as occlusions and textureless regions, producing precise dynamic masks that decouple static and dynamic regions. We then apply a soft key masking scheme that leverages these dynamic masks to suppress interference from dynamic regions in causal attention, thereby improving camera pose estimation accuracy. Stream4D inherits the efficiency of causal attention and remains compatible with existing streaming architectures. On diverse dynamic-scene benchmarks, Stream4D significantly improves camera pose estimation and static-scene reconstruction quality, yields reliable dynamic masks, and effectively mitigates long-sequence ghosting.

Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese

Topics: Computer science, Ghosting, Computer vision, Artificial intelligence, Key (lock), Fuse (electrical)

Sources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange