62 citations · 152 across the 16 of their papers we have counts for
18 papers
Ground-to-Satellite Localization in Unconstrained Image Collections for 3D Scene Reconstruction
Angel Daruna, Ben Southall, Niluthpol Chowdhury Mithun +6
Ground image localization with respect to satellite imagery is a key enabler for metrically-accurate, geo-localized 3D scene reconstruction from unconstrained image collections. Ex…
SGM-SLAM: Scene Graph Matching for Data-Efficient Distributed SLAM
Yewei Huang, Tixiao Shan, Abhinav Rajvanshi +4
We introduce a data-efficient distributed Simultaneous Localization and Mapping (SLAM) framework for multi-robot operation in GPS-denied and communication-constrained environments.…
Efficient Domain-Adaptive Multi-Task Dense Prediction with Vision Foundation Models
Beomseok Kang, Niluthpol Chowdhury Mithun, Mikhail Sizintsev +2
Multi-task dense prediction, which aims to jointly solve tasks like semantic segmentation and depth estimation, is crucial for robotics applications but suffers from domain shift w…
Graph2Nav: 3D Object-Relation Graph Generation to Robot Navigation
Tixiao Shan, Abhinav Rajvanshi, Niluthpol Mithun +1
We propose Graph2Nav, a real-time 3D object-relation graph generation framework, for autonomous navigation in the real world. Our framework fully generates and exploits both 3D obj…
DUDA: Distilled Unsupervised Domain Adaptation for Lightweight Semantic Segmentation
Beomseok Kang, Niluthpol Chowdhury Mithun, Abhinav Rajvanshi +2
Unsupervised Domain Adaptation (UDA) is essential for enabling semantic segmentation in new domains without requiring costly pixel-wise annotations. State-of-the-art (SOTA) UDA met…
Diffusion-Guided Gaussian Splatting for Large-Scale Unconstrained 3D Reconstruction and Novel View Synthesis
Niluthpol Chowdhury Mithun, Tuan Pham, Qiao Wang +6
Recent advancements in 3D Gaussian Splatting (3DGS) and Neural Radiance Fields (NeRF) have achieved impressive results in real-time 3D reconstruction and novel view synthesis. Howe…
Unsupervised Domain Adaptation for Semantic Segmentation with Pseudo Label Self-Refinement
Xingchen Zhao, Niluthpol Chowdhury Mithun, Abhinav Rajvanshi +2
Deep learning-based solutions for semantic segmentation suffer from significant performance degradation when tested on data with different characteristics than what was used during…
C-SFDA: A Curriculum Learning Aided Self-Training Framework for Efficient Source Free Domain Adaptation
Nazmul Karim, Niluthpol Chowdhury Mithun, Abhinav Rajvanshi +3
Unsupervised domain adaptation (UDA) approaches focus on adapting models trained on a labeled source domain to an unlabeled target domain. UDA methods have a strong assumption that…
Cross-View Visual Geo-Localization for Outdoor Augmented Reality
Niluthpol Chowdhury Mithun, Kshitij Minhas, Han-Pang Chiu +4
Precise estimation of global orientation and location is critical to ensure a compelling outdoor Augmented Reality (AR) experience. We address the problem of geo-pose estimation by…
GraphMapper: Efficient Visual Navigation by Scene Graph Generation
Zachary Seymour, Niluthpol Chowdhury Mithun, Han-Pang Chiu +2
Understanding the geometric relationships between objects in a scene is a core capability in enabling both humans and autonomous agents to navigate in new environments. A sparse, u…
SASRA: Semantically-aware Spatio-temporal Reasoning Agent for Vision-and-Language Navigation in Continuous Environments
Muhammad Zubair Irshad, Niluthpol Chowdhury Mithun, Zachary Seymour +3
This paper presents a novel approach for the Vision-and-Language Navigation (VLN) task in continuous 3D environments, which requires an autonomous agent to follow natural language…
Striking the Right Balance: Recall Loss for Semantic Segmentation
Junjiao Tian, Niluthpol Mithun, Zach Seymour +2
Class imbalance is a fundamental problem in computer vision applications such as semantic segmentation. Specifically, uneven class distributions in a training dataset often result…
MaAST: Map Attention with Semantic Transformersfor Efficient Visual Navigation
Zachary Seymour, Kowshik Thopalli, Niluthpol Mithun +3
Visual navigation for autonomous agents is a core task in the fields of computer vision and robotics. Learning-based methods, such as deep reinforcement learning, have the potentia…
RGB2LIDAR: Towards Solving Large-Scale Cross-Modal Visual Localization
Niluthpol Chowdhury Mithun, Karan Sikka, Han-Pang Chiu +2
We study an important, yet largely unexplored problem of large-scale cross-modal visual localization by matching ground RGB images to a geo-referenced aerial LIDAR 3D point cloud (…
Text-based Localization of Moments in a Video Corpus
Sudipta Paul, Niluthpol Chowdhury Mithun, Amit K. Roy-Chowdhury
Prior works on text-based video moment localization focus on temporally grounding the textual query in an untrimmed video. These works assume that the relevant video is already kno…
Weakly Supervised Video Moment Retrieval From Text Queries
Niluthpol Chowdhury Mithun, Sujoy Paul, Amit K. Roy-Chowdhury
There have been a few recent methods proposed in text to video moment retrieval using natural language queries, but requiring full supervision during training. However, acquiring a…
Webly Supervised Joint Embedding for Cross-Modal Image-Text Retrieval
Niluthpol Chowdhury Mithun, Rameswar Panda, Evangelos E. Papalexakis +1
Cross-modal retrieval between visual data and natural language description remains a long-standing challenge in multimedia. While recent image-text retrieval methods offer great pr…
Diversity-aware Multi-Video Summarization
Rameswar Panda, Niluthpol Chowdhury Mithun, Amit K. Roy-Chowdhury
Most video summarization approaches have focused on extracting a summary from a single video; we propose an unsupervised framework for summarizing a collection of videos. We observ…