Hugging Face Trending Papers
Beyond the Image Plane: World-Grounded Queries for Multi-Object Tracking
Read the original on Hugging Face Trending Papers →The Flow has not summarised this story yet — read it at Hugging Face Trending Papers.
Related stories
arXiv AI
Sep 2
Beyond the Image Plane: World-Grounded Queries for Multi-Object Tracking
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.
arXiv Computer Vision
Oct 2
ARROW: Arbitrary Reconstruction and Tracking of 4D Observations in the Wild
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...
arXiv AI
Sep 25
TrackEverything: Long Horizon Dense Tracking via De-Duplicating 3D Scene Representations
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.
Hugging Face Trending Papers
Jun 24
MVTrack4Gen: Multi-View Point Tracking as Geometric Supervision for 4D Video Generation
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 Computer Vision
Sep 17
Online Multi-Camera 3D Tracking via ID Prediction over Recurrent Sparse Queries
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...
arXiv AI
Jun 30
Beyond 2D Matching: A Unified Single-Stage Framework for Geometry-Aware Cross-View Object Geo-Localization
arXiv:2606. 30576v1 Announce Type: cross Abstract: Cross-view object geo-localization (CVOGL) aims to locate a target object from a query view (e.