Newest papers

HiP3R: Hierarchical Pose Graphs for Long-Horizon 3D Reconstruction

Zunnan Xu, Shangchen Zhou, Yihang Luo, Chen Change Loy · 2026 · arXiv (Cornell University)

DOI: 10.48550/arxiv.2610.31635 · cited by 0 works (OpenAlex) · open-access PDF

Korean

짧은 비디오 윈도우에서 카메라 움직임과 3D 프레임 기하학을 정확하게 추정합니다. 그러나 계산 및 메모리 비용은 수천 개의 프레임을 포함하는 얇은 시퀀스에 직접적인 추론을 방지합니다. 긴 비디오는 다루는 조각으로 처리해야합니다. 이 분할은 불일치 좌표 프레임과 일관된 3D 기하학을 생산합니다. 글로벌 일관성을 달성하기 위해서는 인접한 프레임의 오류 또는 충돌 예측으로부터 직접적인 제한을 확산해야합니다. 이 요구 사항은 자연스럽게 그래픽 최적화를 동기화합니다. 그러나 그래픽 수준의 선택은 거래를 창출합니다. Chunk-level 그래프레임은 효율적으로 스케일 드라이브를 해결하고

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

Abstract

Feed-forward models accurately estimate camera motion and 3D geometry from short video windows. However, computational and memory costs prevent direct inference on sequences containing thousands of frames. Long videos must therefore be processed as overlapping chunks. This division produces independent local reconstructions with inconsistent coordinate frames and duplicate estimates of shared cameras. Achieving global consistency requires propagating constraints from adjacent overlaps and distant revisits across the sequence. This requirement naturally motivates pose graph optimization. However, the choice of graph level creates a trade-off. Chunk-level graphs efficiently resolve scale drift and close large loops. Yet, their rigid transformations cannot correct internal errors or conflicting frame predictions. Conversely, frame-level optimization offers local flexibility, but scaling it globally is computationally expensive and can break metric scale. HiP3R resolves this trade-off using a hierarchical pose graph. HiP3R first optimizes a robust chunk-level $\mathrm{Sim}(3)$ graph to establish the global layout and scale. It then holds this layout fixed and estimates one shared $\mathrm{SE}(3)$ camera per frame, turning overlapping window predictions into a single trajectory. Experiments across multiple benchmarks demonstrate the effectiveness of HiP3R in improving camera trajectories and 3D reconstruction. Our method applies to both chunk-based and streaming backends without additional training or fine-tuning. The codes are available at https://kkakkkka.github.io/HiP3R.

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

Topics: Computer science, Graph, Inference, Artificial intelligence, Metric (unit), Computer vision

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