Search Results for author: Rohit Mohan

Found 15 papers, 4 papers with code

Panoptic Out-of-Distribution Segmentation

no code implementations18 Oct 2023 Rohit Mohan, Kiran Kumaraswamy, Juana Valeria Hurtado, Kürsat Petek, Abhinav Valada

Deep learning has led to remarkable strides in scene understanding with panoptic segmentation emerging as a key holistic scene interpretation task.

Data Augmentation Instance Segmentation +3

AmodalSynthDrive: A Synthetic Amodal Perception Dataset for Autonomous Driving

no code implementations12 Sep 2023 Ahmed Rida Sekkat, Rohit Mohan, Oliver Sawade, Elmar Matthes, Abhinav Valada

To address these limitations, we introduce AmodalSynthDrive, a synthetic multi-task multi-modal amodal perception dataset.

Autonomous Driving Benchmarking +2

Perceiving the Invisible: Proposal-Free Amodal Panoptic Segmentation

no code implementations29 May 2022 Rohit Mohan, Abhinav Valada

Amodal panoptic segmentation aims to connect the perception of the world to its cognitive understanding.

Amodal Panoptic Segmentation Panoptic Segmentation

Amodal Panoptic Segmentation

no code implementations CVPR 2022 Rohit Mohan, Abhinav Valada

To enable robots to reason with this capability, we formulate and propose a novel task that we name amodal panoptic segmentation.

Amodal Panoptic Segmentation Instance Segmentation +2

7th AI Driving Olympics: 1st Place Report for Panoptic Tracking

no code implementations9 Dec 2021 Rohit Mohan, Abhinav Valada

In this technical report, we describe our EfficientLPT architecture that won the panoptic tracking challenge in the 7th AI Driving Olympics at NeurIPS 2021.

Benchmarking Panoptic Segmentation +1

EfficientLPS: Efficient LiDAR Panoptic Segmentation

no code implementations16 Feb 2021 Kshitij Sirohi, Rohit Mohan, Daniel Büscher, Wolfram Burgard, Abhinav Valada

Panoptic segmentation of point clouds is a crucial task that enables autonomous vehicles to comprehend their vicinity using their highly accurate and reliable LiDAR sensors.

Autonomous Vehicles Instance Segmentation +2

Robust Vision Challenge 2020 -- 1st Place Report for Panoptic Segmentation

no code implementations23 Aug 2020 Rohit Mohan, Abhinav Valada

In this technical report, we present key details of our winning panoptic segmentation architecture EffPS_b1bs4_RVC.

Benchmarking Panoptic Segmentation +1

MOPT: Multi-Object Panoptic Tracking

no code implementations17 Apr 2020 Juana Valeria Hurtado, Rohit Mohan, Wolfram Burgard, Abhinav Valada

In this paper, we introduce a novel perception task denoted as multi-object panoptic tracking (MOPT), which unifies the conventionally disjoint tasks of semantic segmentation, instance segmentation, and multi-object tracking.

Instance Segmentation Multi-Object Tracking +3

EfficientPS: Efficient Panoptic Segmentation

2 code implementations5 Apr 2020 Rohit Mohan, Abhinav Valada

Understanding the scene in which an autonomous robot operates is critical for its competent functioning.

Instance Segmentation Panoptic Segmentation +1

Vision-Based Autonomous UAV Navigation and Landing for Urban Search and Rescue

no code implementations4 Jun 2019 Mayank Mittal, Rohit Mohan, Wolfram Burgard, Abhinav Valada

This problem is extremely challenging as pre-existing maps cannot be leveraged for navigation due to structural changes that may have occurred.


Self-Supervised Model Adaptation for Multimodal Semantic Segmentation

1 code implementation11 Aug 2018 Abhinav Valada, Rohit Mohan, Wolfram Burgard

To address this limitation, we propose a mutimodal semantic segmentation framework that dynamically adapts the fusion of modality-specific features while being sensitive to the object category, spatial location and scene context in a self-supervised manner.

Scene Recognition Semantic Segmentation

Cannot find the paper you are looking for? You can Submit a new open access paper.