Skip to main navigation Skip to search Skip to main content

DINTR: Tracking via Diffusion-based Interpolation

  • Pha Nguyen
  • , Ngan Le
  • , Jackson Cothren
  • , Alper Yilmaz
  • , Khoa Luu

Research output: Contribution to journal › Conference article › peer-review

Abstract

Object tracking is a fundamental task in computer vision, requiring the localization of objects of interest across video frames. Diffusion models have shown remarkable capabilities in visual generation, making them well-suited for addressing several requirements of the tracking problem. This work proposes a novel diffusion-based methodology to formulate the tracking task. Firstly, their conditional process allows for injecting indications of the target object into the generation process. Secondly, diffusion mechanics can be developed to inherently model temporal correspondences, enabling the reconstruction of actual frames in video. However, existing diffusion models rely on extensive and unnecessary mapping to a Gaussian noise domain, which can be replaced by a more efficient and stable interpolation process. Our proposed interpolation mechanism draws inspiration from classic image-processing techniques, offering a more interpretable, stable, and faster approach tailored specifically for the object tracking task. By leveraging the strengths of diffusion models while circumventing their limitations, our Diffusion-based INterpolation TrackeR (DINTR) presents a promising new paradigm and achieves a superior multiplicity on seven benchmarks across five indicator representations.

Original languageEnglish
JournalAdvances in Neural Information Processing Systems
Volume37
StatePublished - 2024
Event38th Conference on Neural Information Processing Systems, NeurIPS 2024 - Vancouver, Canada
Duration: Dec 9 2024 → Dec 15 2024

Fingerprint

Dive into the research topics of 'DINTR: Tracking via Diffusion-based Interpolation'. Together they form a unique fingerprint.

Cite this