paper-with-me

홈 › Papers

Tracking Everything Everywhere All at Once

2023-06-08 · ICCV 2023 1 · Qianqian Wang, Yen-Yu Chang, Ruojin Cai, Zhengqi Li, Bharath Hariharan, Aleksander Holynski, Noah Snavely

We present a new test-time optimization method for estimating dense and long-range motion from a video sequence. Prior optical flow or particle video tracking algorithms typically operate within limited temporal windows, struggling to track through occlusions and maintain global consistency of estimated motion trajectories. We propose a complete and globally consistent motion representation, dubbed OmniMotion, that allows for accurate, full-length motion estimation of every pixel in a video. OmniMotion represents a video using a quasi-3D canonical volume and performs pixel-wise tracking via bijections between local and canonical space. This representation allows us to ensure global consistency, track through occlusions, and model any combination of camera and object motion. Extensive evaluations on the TAP-Vid benchmark and real-world footage show that our approach outperforms prior state-of-the-art methods by a large margin both quantitatively and qualitatively. See our project page for more results: http://omnimotion.github.io/

📄 PDF Abstract BibTeX arXiv:2306.05422

Code (1)

qianqianwang68/omnimotion 공식 구현 pytorch

Tasks

AllMotion EstimationOptical Flow Estimation

Similar Papers 제목 키워드 기반

Segment Everything Everywhere All at Once

2023-04-13 · NeurIPS 2023 11 · Xueyan Zou, Jianwei Yang, Hao Zhang, Feng Li 외

In this work, we present SEEM, a promptable and interactive model for segmenting everything everywhere all at once in an image, as shown in Fig.1. In SEEM, we propose a novel decoding mechanism that enables diverse promp…

AllDecoderImage SegmentationInteractive Segmentation+5

Evaluating the Robustness of the "Ensemble Everything Everywhere" Defense

2024-11-22 · Jie Zhang, Christian Schlarmann, Kristina Nikolić, Nicholas Carlini 외

Ensemble everything everywhere is a defense to adversarial examples that was recently proposed to make image classifiers robust. This defense works by ensembling a model's intermediate representations at multiple noisy i…

Adversarial AttackRobust classification

Track Everything Everywhere Fast and Robustly

2024-03-26 · Yunzhou Song, Jiahui Lei, ZiYun Wang, Lingjie Liu 외

We propose a novel test-time optimization approach for efficiently and robustly tracking any pixel at any time in a video. The latest state-of-the-art optimization-based tracking technique, OmniMotion, requires a prohibi…

Depth EstimationInductive BiasMonocular Depth Estimation

Querying Everything Everywhere All at Once: Supervaluationism for the Agentic Lakehouse

2026-03-11 · Jacopo Tagliabue arxiv

Agentic analytics is turning the lakehouse into a multi-version system: swarms of (human or AI) producers materialize competing pipelines in data branches, while (human or AI) consumers need answers without knowing the u…

Decomposition Betters Tracking Everything Everywhere

2024-07-09 · Rui Li, Dong Liu

Recent studies on motion estimation have advocated an optimized motion representation that is globally consistent across the entire video, preferably for every pixel. This is challenging as a uniform representation may n…

Motion EstimationPoint Tracking