# Detachable Object Detection: Segmentation and Depth Ordering From Short-Baseline Video

Source: [Detachable Object Detection: Segmentation and Depth Ordering From Short-Baseline Video](<https://www.sota2.com/research/paper/68fa60561e209131ce9eedbd>)

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

Data updated: 2025-10-25T19:37:40.397Z

Authors: Alper Ayvaci, Stefano Soatto

Published: 2011-09-22T00:55:32.000Z

## Abstract

We describe an approach for segmenting an image into regions that correspond to surfaces in the scene that are partially surrounded by the medium. It integrates both appearance and motion statistics into a cost functional, that is seeded with occluded regions and minimized efficiently by solving a linear programming problem. Where a short observation time is insufficient to determine whether the object is detachable, the results of the minimization can be used to seed a more costly optimization based on a longer sequence of video data. The result is an entirely unsupervised scheme to detect and segment an arbitrary and unknown number of objects. We test our scheme to highlight the potential, as well as limitations, of our approach.

## 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/1109.4683>)

[PDF](<https://arxiv.org/pdf/1109.4683.pdf>)
