The paper introduces an on-the-fly homography calibration system for multi-camera tracking that starts from coarse manual homographies and refines them using a centroid-based projection optimization (PO) on live detection metadata. PO continuously aligns ground-plane geometry without adding computational latency, enabling the system to adapt automatically to camera movements or environmental changes. The refined geometry feeds a bird's-eye-view tracker that fuses detections and unifies trajectories across zones while maintaining privacy safety and zero overhead.
By David Voihanski, Mor Sinai, Ben Zion Bobrovsky
Precise multi-camera tracking traditionally relies on rigorous 3D site calibration, yet this requirement is often operationally impossible in large-scale deployments. Privacy regulations frequently pr...
WorldCast introduces a distributed multiplayer world model where each player runs a local client that generates video and estimates player position from recorded data. Clients share only player and scene states, allowing them to project these states into camera-aligned fields that guide rendering of other players. This approach achieves real‑time performance, improves rendering rates by over an order of magnitude, and maintains visual consistency across views without a centralized computational bottleneck.
By Ziyang Ye, Junchao Huang, Evelyn Zhang, Zhihao Xie, Ruicheng Zhang, Boyao Han, Litao Ban, Ziye Wang, Xinting Hu, Shaoshuai Shi, Zhuotao Tian, Li Jiang
Momentum introduces a two-stage pipeline for video world models that uses synchronized multi-camera rigs to represent evolving scenes. The WorldUpdate stage generates shared reference-camera videos as a memory of scene dynamics, while WorldInteract grounds target camera video generation in this memory, ensuring moving objects remain represented outside the field of view. Experiments on CARLA street scenes show a 126.2% improvement in dynamic scene consistency over static image conditioning.
By Nedko Savov, Stefan Maria Ailuro, Danda Pani Paudel, Yilun Du, Xi Wang, Luc Van Gool
WorldCraft is an autoregressive video world model that enables both camera navigation and persistent object-trajectory control in interactive video environments. It introduces Normalized World Trajectory (NWT) to anchor user-specified 2D motion paths in a world coordinate system, and Trajectory-Anchored State Persistence (TASP) to maintain updated object states even when the target is temporarily invisible. The model also employs a pathway-selective LoRA to add object control while preserving pretrained camera navigation capabilities, achieving accurate composable control and maintaining object states across extended off-screen intervals.
By Bohai Gu, Taiyi Wu, Yueyang Yuan, Jian Liu, Xiaocheng Lu, Dazhao Du, Jie Zhang, Jinxiang Lai, Shuai Yang, Xiaotong Zhao, Alan Zhao, Song Guo
ReWorld-Track introduces a recursive event world model for language‑guided multi‑camera tracking that explicitly carries association uncertainty into future predictions. By treating candidate matches and waiting as alternative target states, the model updates a persistent recurrent belief that preserves uncertainty across successive observations. This approach improves identity continuity and next‑camera accuracy, achieving HOTA scores of 65.19 on CityFlowV2 and 45.36 on MTMMC, and reducing median arrival‑time error from 0.78 s to 0.71 s.
By Haoyang Wu, Shoudong Han, Chaoyue Li, Sijia Chen, Zhenyang Xie, Wang sihan
The paper introduces MvT, a training‑free multi‑view pipeline for event‑camera based multiple object tracking. MvT preserves the 2‑D event format while generating three complementary spatio‑temporal views, then fuses them into a 3‑D coordinate system to resolve tracking ambiguities that arise in single‑view pseudo‑frames. Experiments on four datasets, including a new Small Objects Dataset, show that MvT outperforms both non‑learning and learning trackers and can be applied when ground‑truth annotations are unavailable.
By Muxi Zha, Banglei Guan, Minzu Liang, Zibin Liu, Yang Shang, Qifeng Yu, Laurent Kneip
arXiv:2509. 08421v2 Announce Type: replace-cross Abstract: For multimedia spatial intelligence through time, multi-view multi-object tracking (MVMOT) suffers from persistent challenges in maintaining consistent object identities across different camera views, leading to tracking inaccuracies.
By Keisuke Toida, Taigo Sakai, Takeshi Nakamura, Hiroshi Shimizu, Kazuhiro Hotta
arXiv:2609.18363v1 Announce Type: new
Abstract: Online multi camera 3D tracking must maintain scene global identities across synchronized views, yet query-based trackers carry these identities only i...
By Pragyan Shrestha, Haruto Nakayama, Atom Scott
GRACE is a camera‑efficient multi‑view pedestrian tracker that reduces the number of required cameras while maintaining high tracking accuracy. It combines volumetric‑guided fusion of homography‑based BEV features with 3D‑lifted features, uses ray conditioning to incorporate each camera’s viewing direction, and employs BEV Track Recovery to continue existing tracks with low‑confidence detections. On the WildTrack dataset, GRACE raises MOTA from 83.54 to 91.07 compared to the baseline TrackTacular.
By Taigo Sakai, Kazuhiro Hotta, Hiroki Kouno, Naoki Kato
The paper introduces a reliability-regulated trajectory optimization framework for progressive COLMAP‑free 3D Gaussian Splatting (3DGS). It uses a self‑supervised bidirectional cycle‑consistency mechanism to control camera trajectory estimation through forward motion propagation and retrospective trajectory correction, thereby reducing error compounding without external priors. Experiments on Tanks and Temples and CO3D‑V2 demonstrate improved camera trajectory accuracy and novel‑view rendering quality compared to existing unposed baselines.
By Zijian Wu, Jinliang Wang, Zidian Lin, Ying Song, Ziqian Lu, Hanjie Ma, Zhen Ye, Mingfeng Jiang
HiP3R introduces a hierarchical pose graph approach for long‑horizon 3D reconstruction, addressing the trade‑off between chunk‑level and frame‑level optimization. It first builds a robust chunk‑level Sim(3) graph to set the global layout and scale, then fixes this layout while estimating a single SE(3) camera pose per frame to merge overlapping predictions into a unified trajectory. Experiments on multiple benchmarks show that HiP3R improves camera trajectories and 3D reconstruction quality for both chunk‑based and streaming backends without extra training.
By Zunnan Xu, Shangchen Zhou, Yihang Luo, Chen Change Loy