activity
20182024
collaborators
Showing cs.CVShow all

5 papers · 1 filter

cs.CV2024

Point-VOS: Pointing Up Video Object Segmentation

Idil Esen Zulfikar, Sabarinath Mahadevan, Paul Voigtlaender +1

Current state-of-the-art Video Object Segmentation (VOS) methods rely on dense per-object mask annotations both during training and testing. This requires time-consuming and costly…

cs.CV2023

AGILE3D: Attention Guided Interactive Multi-object 3D Segmentation

Yuanwen Yue, Sabarinath Mahadevan, Jonas Schult +4

During interactive segmentation, a model and a user work together to delineate objects of interest in a 3D point cloud. In an iterative process, the model assigns each data point t…

cs.CV2023

DynaMITe: Dynamic Query Bootstrapping for Multi-object Interactive Segmentation Transformer

Amit Kumar Rana, Sabarinath Mahadevan, Alexander Hermans +1

Most state-of-the-art instance segmentation methods rely on large amounts of pixel-precise ground-truth annotations for training, which are expensive to create. Interactive segment…

cs.CV2022

4D-StOP: Panoptic Segmentation of 4D LiDAR using Spatio-temporal Object Proposal Generation and Aggregation

Lars Kreuzberg, Idil Esen Zulfikar, Sabarinath Mahadevan +2

In this work, we present a new paradigm, called 4D-StOP, to tackle the task of 4D Panoptic LiDAR Segmentation. 4D-StOP first generates spatio-temporal proposals using voting-based…

cs.CV2018

Iteratively Trained Interactive Segmentation

Sabarinath Mahadevan, Paul Voigtlaender, Bastian Leibe

Deep learning requires large amounts of training data to be effective. For the task of object segmentation, manually labeling data is very expensive, and hence interactive methods…