ArTIST: Autoregressive Trajectory Inpainting and Scoring for Tracking
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.
Code (0)
등록된 구현이 없습니다.
Tasks
Human motion predictionmotion predictionMultiple Object TrackingObject TrackingSimilar Papers 제목 키워드 기반
PaintCopilot: Modeling Painting as Autonomous Artistic Continuation
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
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 TrackingGuidefill: GPU Accelerated, Artist Guided Geometric Inpainting for 3D Conversion
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…
GPUThe Piano Inpainting Application
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…
DecoderSee4D: Pose-Free 4D Generation via Auto-Regressive Video Inpainting
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