# A Generalist Framework for Panoptic Segmentation of Images and Videos

Source: [A Generalist Framework for Panoptic Segmentation of Images and Videos](<https://www.sota2.com/research/paper/68fa70d31e209131cea4d72e>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-26T01:50:52.513Z

Authors: Ting Chen, Lala Li, Saurabh Saxena, Geoffrey Hinton, David J. Fleet

Published: 2022-10-12T16:18:25.000Z

## Abstract

Panoptic segmentation assigns semantic and instance ID labels to every pixel of an image. As permutations of instance IDs are also valid solutions, the task requires learning of high-dimensional one-to-many mapping. As a result, state-of-the-art approaches use customized architectures and task-specific loss functions. We formulate panoptic segmentation as a discrete data generation problem, without relying on inductive bias of the task. A diffusion model is proposed to model panoptic masks, with a simple architecture and generic loss function. By simply adding past predictions as a conditioning signal, our method is capable of modeling video (in a streaming setting) and thereby learns to track object instances automatically. With extensive experiments, we demonstrate that our simple approach can perform competitively to state-of-the-art specialist methods in similar settings.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2210.06366>)

[PDF](<https://arxiv.org/pdf/2210.06366.pdf>)
