paper-with-me

홈 › Papers

ArTIST: Autoregressive Trajectory Inpainting and Scoring for Tracking

2020-04-16 · Fatemeh Saleh, Sadegh Aliakbarian, Mathieu Salzmann, Stephen Gould

One of the core components in online multiple object tracking (MOT) frameworks is associating new detections with existing tracklets, typically done via a scoring function. Despite the great advances in MOT, designing a reliable scoring function remains a challenge. In this paper, we introduce a probabilistic autoregressive generative model to score tracklet proposals by directly measuring the likelihood that a tracklet represents natural motion. One key property of our model is its ability to generate multiple likely futures of a tracklet given partial observations. This allows us to not only score tracklets but also effectively maintain existing tracklets when the detector fails to detect some objects even for a long time, e.g., due to occlusion, by sampling trajectories so as to inpaint the gaps caused by misdetection. Our experiments demonstrate the effectiveness of our approach to scoring and inpainting tracklets on several MOT benchmark datasets. We additionally show the generality of our generative model by using it to produce future representations in the challenging task of human motion prediction.

📄 PDF Abstract BibTeX arXiv:2004.07482

Code (0)

등록된 구현이 없습니다.

Tasks

Human motion predictionmotion predictionMultiple Object TrackingObject Tracking

Similar Papers 제목 키워드 기반

PaintCopilot: Modeling Painting as Autonomous Artistic Continuation

2026-05-20 · Yunge Wen, Yuancheng Shen, Paul Pu Liang arxiv

We present PaintCopilot, a co-creative neural painting assistant that models painting as an open-ended autoregressive artistic behavior conditioned on evolving canvas states and prior brushstroke history, without requiri…

Probabilistic Tracklet Scoring and Inpainting for Multiple Object Tracking

2020-12-03 · CVPR 2021 1 · Fatemeh Saleh, Sadegh Aliakbarian, Hamid Rezatofighi, Mathieu Salzmann 외

Despite the recent advances in multiple object tracking (MOT), achieved by joint detection and tracking, dealing with long occlusions remains a challenge. This is due to the fact that such techniques tend to ignore the l…

Multiple Object TrackingObject Tracking

Guidefill: GPU Accelerated, Artist Guided Geometric Inpainting for 3D Conversion

2016-11-16 · L. Robert Hocking, Russell MacKenzie, Carola-Bibiane Schoenlieb

The conversion of traditional film into stereo 3D has become an important problem in the past decade. One of the main bottlenecks is a disocclusion step, which in commercial 3D conversion is usually done by teams of arti…

GPU

The Piano Inpainting Application

2021-07-13 · Gaëtan Hadjeres, Léopold Crestel

Autoregressive models are now capable of generating high-quality minute-long expressive MIDI piano performances. Even though this progress suggests new tools to assist music composition, we observe that generative algori…

Decoder

See4D: Pose-Free 4D Generation via Auto-Regressive Video Inpainting

2025-10-30 · Dongyue Lu, Ao Liang, Tianxin Huang, Xiao Fu 외 arxiv

Immersive applications call for synthesizing spatiotemporal 4D content from casual videos without costly 3D supervision. Existing video-to-4D methods typically rely on manually annotated camera poses, which are labor-int…

Trajectory PredictionVideo GenerationVideo Inpainting