The paper introduces PLANET, a multi‑object tracker that transcends traditional image‑plane limitations by incorporating 3D scene geometry into its query formation. By lifting 2D tracking datasets into 3D and embedding reconstructed geometry into features and positional encodings, PLANET encourages queries to encode object positions. An auxiliary 3D location prediction task and a dual‑resolution temporal memory further enhance performance, enabling state‑of‑the‑art results on three diverse benchmarks.
By Orcun Cetintas, Guillem Bras\'o, Tim Meinhardt, Laura Leal-Taix\'e
arXiv:2610.01314v1 Announce Type: new
Abstract: Dynamic scenes may be captured by a moving camera, multiple video streams, or images taken at different times. These observations reveal complementary...
By Ilya Fradlin, Christian Schmidt, Jens Piekenbrinck, Karim Knaebel, Gonzalo Martin Garcia, Bastian Leibe
TrackEverything is a 3D point tracker that overcomes the trade‑off between sparse long‑horizon tracking and dense short‑clip tracking by representing videos as persistent 3D scene tracks in world coordinates. It introduces voxel‑based de‑duplication at sliding‑window boundaries, a two‑stage refinement process (endpoint refiner and lightweight trajectory refiner), and a 3D WAFT module that replaces memory‑heavy 4D correlation volumes with efficient feature sampling. The method can track all visible points in videos longer than 1000 frames using only 40 GB of GPU memory, outperforming existing dense trackers on short clips and matching sparse trackers on long sequences.
By Ayush Jain, Sreeharsha Paruchuri, Ishita Gupta, Fan Zhang, Tanner Schmidt, Jakob Engel, Katerina Fragkiadaki, Adam W. Harley
Synthesizing a novel-view video from a monocular reference video along a target camera trajectory requires both geometric consistency and motion fidelity with respect to the reference video. Existing methods based on explicit 3D representations are limited by the accuracy of off-the-shelf reconstruction modules, which often produce inaccurate geometry for dynamic objects in monocular videos.
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
arXiv:2606. 30576v1 Announce Type: cross Abstract: Cross-view object geo-localization (CVOGL) aims to locate a target object from a query view (e.
By Liyao Wang, Ruipu Wu, Haojun Xu, Lei Shi, Linjiang Huang, Si Liu
The paper introduces LingGS, an online monocular RGB Gaussian splatting SLAM system that decouples feed‑forward geometry prediction from camera tracking. By leveraging a frozen streaming 3D foundation model as a virtual RGB‑D sensor for depth estimation and an explicit geometric solver for camera motion via feature reprojection, LingGS achieves higher tracking accuracy than learned predictions. Experiments on indoor and outdoor datasets demonstrate significant improvements in reconstruction quality, achieving about 7 FPS on a single RTX 4090 and 2–3× the throughput of prior SLAM systems.
By Da Li, Yihan Zang, Ivan Viola, Zeyu Wang, Dominik Engel
arXiv:2607. 17778v1 Announce Type: cross Abstract: Class-agnostic 3D instance segmentation is critical for robotic systems operating in unknown environments, enabling perception of previously unseen objects for reliable manipulation and navigation.
By Juno Kim, Hye-Jung Yoon, Yesol Park, Byoung-Tak Zhang
The paper introduces XTrack, a unified framework that repurposes a pretrained video Diffusion Transformer (DiT) for cross-view temporal object correspondence. XTrack incorporates focal cross-view attention alignment, hard negative conditioning, and local context cropping to improve grounding across views and time, and it uses a pseudo‑label curation pipeline to generate dense supervision from sparse Ego‑Exo4D data. The authors demonstrate that XTrack achieves robust temporal consistency and identity preservation in cross‑view tracking tasks.
By Siyoon Jin, Dahyun Chung, Honggyu An, Sangbeom Lim, Wonjin Nam, Jaewoo Jung, WonJun Moon, Seungryong Kim
MoSE3 is a feed‑forward model that predicts dense SE(3) motion—full 6‑DoF rigid transforms—at every pixel from monocular RGB video, providing rotation, translation, and grouping information simultaneously. It achieves this by jointly learning 3D point tracks and rigidity embeddings, then differentiably fitting transforms within soft rigid clusters. The authors also release Art‑Kubric, a large synthetic dataset with dense SE(3) and rigidity labels, and demonstrate state‑of‑the‑art performance on both rigid and articulated benchmarks, with strong generalization to real‑world videos.
By Jiahuan Cheng, Zhiyi Li, Tian Xia, Ruojin Cai, Yilun Du, Qianqian Wang
Class-agnostic 3D instance segmentation is critical for robotic systems operating in unknown environments, enabling perception of previously unseen objects for reliable manipulation and navigation. Existing approaches typically project per-frame 2D instance masks into 3D and merge them, which often breaks object identities across time and yields fragmented 3D instances.
MAETrack introduces a lightweight framework to adapt pretrained masked autoencoder (MAE) representations for 3D single object tracking (SOT). It uses Layer‑Selective Initialization (LSI) to keep shallow geometric layers from the pre‑training while re‑initializing deeper layers, and Geometric Residual Gating (GRG) to emphasize salient regions in BEV features before template‑search fusion. Experiments on standard 3D SOT benchmarks show consistent improvements over vanilla fine‑tuning with minimal computational cost.
By Sifan Zhou, Qiwei Wang, Linyue Tan, Ziyu Liu, Ziyu Zhao, Xiaobo Lu