Explanipedia

MONITRS: Multimodal Observations of Natural Incidents Through Remote Sensing Open

Shreelekha Revankar, Utkarsh Mall, Cheng Perng Phoo, Kavita Bala, Bharath Hariharan · 2025

Natural disasters cause devastating damage to communities and infrastructure every year. Effective disaster response is hampered by the difficulty of accessing affected areas during and after events. Remote sensing has allowed us to monito…

A one-pot solvothermal method for the synthesis of a magnetically retrievable ZnFe2O4 incorporated biphase TiO2 photocatalyst for robust efficient solar fuel (hydrogen) production Open

Hafeez Yusuf Hafeez, Kavita Bala, Umar Muhammad Dankawu, J. Mohammed, Abdussalam Balarabe Suleiman , et al. · 2025

In response to the worldwide energy problem and environmental contamination that hinders any society's ability to develop. Herein, a 1-pot solvothermal approach was used to fabricate a ZnFe2O4 integrated biphase TiO2 photocatalyst for use …

DiSciPLE: Learning Interpretable Programs for Scientific Visual Discovery Open

Utkarsh Mall, Cheng Perng Phoo, Mia Chiquier, Bharath Hariharan, Kavita Bala , et al. · 2025

Visual data is used in numerous different scientific workflows ranging from remote sensing to ecology. As the amount of observation data increases, the challenge is not just to make accurate predictions but also to understand the underlyin…

AllClear: A Comprehensive Dataset and Benchmark for Cloud Removal in Satellite Imagery Open

Hangyu Zhou, Chia-Hsiang Kao, Cheng Perng Phoo, Utkarsh Mall, Bharath Hariharan , et al. · 2024

Clouds in satellite imagery pose a significant challenge for downstream applications. A major challenge in current cloud removal research is the absence of a comprehensive benchmark and a sufficiently large and diverse training dataset. To…

Scale-Aware Recognition in Satellite Images under Resource Constraints Open

Shreelekha Revankar, Cheng Perng Phoo, Utkarsh Mall, Bharath Hariharan, Kavita Bala · 2024

Recognition of features in satellite imagery (forests, swimming pools, etc.) depends strongly on the spatial scale of the concept and therefore the resolution of the images. This poses two challenges: Which resolution is best suited for re…

Enhancing syphilis diagnosis through innovative adaptation of wet mount microscopy Open

Senkadhir Vendhan, Biju Vasudevan, Kavita Bala, Shekhar Neema · 2024

Remote Sensing Vision-Language Foundation Models without Annotations via Ground Remote Alignment Open

Utkarsh Mall, Cheng Perng Phoo, Meilin Kelsey Liu, Carl Vondrick, Bharath Hariharan , et al. · 2023

We introduce a method to train vision-language models for remote-sensing images without using any textual annotations. Our key insight is to use co-located internet imagery taken on the ground as an intermediary for connecting remote-sensi…

Design and Fabrication of a Dual Condition PIN-ON-DISC Automated Wear Testing Machine Open

Uhuami Abdulwahab, Mohammed Baba Ndaliman, Oluwafemi Ayodeji Olugboji, Kavita Bala · 2023

Wear is a dynamic and complex process that involves not only surface and material properties but operating conditions as well.Wearing of surfaces may lead to extra cost of maintenance or manufacturing process.This paper presents the design…

"An Approach To Discover Similar Musical Patterns Using Natural Language Processing " Open

S. Nyamathulla, Kavita Bala · 2023

Activation Regression for Continuous Domain Generalization with Applications to Crop Classification Open

Samar Khanna, Bram Wallace, Kavita Bala, Bharath Hariharan · 2022

Geographic variance in satellite imagery impacts the ability of machine learning models to generalise to new regions. In this paper, we model geographic generalisation in medium resolution Landsat-8 satellite imagery as a continuous domain…

Discovering Underground Maps from Fashion Open

Utkarsh Mall, Kavita Bala, Tamara L. Berg, Kristen Grauman · 2022

The fashion sense -- meaning the clothing styles people wear -- in a geographical region can reveal information about that region. For example, it can reflect the kind of activities people do there, or the type of crowds that frequently vi…

Field-Guide-Inspired Zero-Shot Learning Open

Utkarsh Mall, Bharath Hariharan, Kavita Bala · 2021

Modern recognition systems require large amounts of supervision to achieve accuracy. Adapting to new domains requires significant data from experts, which is onerous and can become too expensive. Zero-shot learning requires an annotated se…

Author Index Open

Aakanksha Aakanksha, Pieter Abbeel, Abd-Almageed Wael, Shahira Abousamra, Abrahamyan Lusine , et al. · 2021

AutoPhoto: Aesthetic Photo Capture using Reinforcement Learning Open

Hadi AlZayer, Hubert Lin, Kavita Bala · 2021

The process of capturing a well-composed photo is difficult and it takes years of experience to master. We propose a novel pipeline for an autonomous agent to automatically capture an aesthetic photograph by navigating within a local regio…

Learning From Paintings Improves Representations for Fabric Recognition Open

Hubert Lin, Mitchell van Zuijlen, Maarten Wijntjes, Sylvia C. Pont, Kavita Bala · 2021

Material classification is the task of distinguishing materials like fabric, wood, ceramic, and so forth. Fine-grained classification aims to distinguish subcategories of a material (e.g., satin fabric versus wool fabric). Fine-grained rec…

Painterly depictions of glasses display a stylized pattern of highlights Open

Mitchell van Zuijlen, Hubert Lin, Kavita Bala, Sylvia C. Pont, Maarten Wijntjes · 2021

For a painterly depiction to be convincing, the distal world does not need to be captured perfectly: a stylistic depiction that does not adhere to the statistical regularities found in the distal world can nevertheless be perceptually conv…

Materials In Paintings (MIP): An interdisciplinary dataset for perception, art history, and computer vision Open

Mitchell van Zuijlen, Hubert Lin, Kavita Bala, Sylvia C. Pont, Maarten Wijntjes · 2021

In this paper, we capture and explore the painterly depictions of materials to enable the study of depiction and perception of materials through the artists’ eye. We annotated a dataset of 19k paintings with 200k+ bounding boxes from which…

Guest Editorial: Introduction to the Special Section on Computational Photography Open

Yoav Y. Schechner, Kavita Bala, Ori Katz, Kalyan Sunkavalli, Ko Nishino · 2021

The papers in this special section focus on computational photography. The past year has been significant in many ways. For the scientific community of computational photography, we have a hybrid in-person conference, one of the first in t…

PhySG: Inverse Rendering with Spherical Gaussians for Physics-based Material Editing and Relighting Open

Kai Zhang, Fujun Luan, Qianqian Wang, Kavita Bala, Noah Snavely · 2021

We present PhySG, an end-to-end inverse rendering pipeline that includes a fully differentiable renderer and can reconstruct geometry, materials, and illumination from scratch from a set of RGB input images. Our framework represents specul…

PiCIE: Unsupervised Semantic Segmentation using Invariance and Equivariance in Clustering Open

Jang Hyun Cho, Utkarsh Mall, Kavita Bala, Bharath Hariharan · 2021

We present a new framework for semantic segmentation without annotations via clustering. Off-the-shelf clustering methods are limited to curated, single-label, and object-centric images yet real-world data are dominantly uncurated, multi-l…

PhySG: Inverse Rendering with Spherical Gaussians for Physics-based\n Material Editing and Relighting Open

Kai Zhang, Fujun Luan, Qianqian Wang, Kavita Bala, Noah Snavely · 2021

We present PhySG, an end-to-end inverse rendering pipeline that includes a\nfully differentiable renderer and can reconstruct geometry, materials, and\nillumination from scratch from a set of RGB input images. Our framework\nrepresents spe…

PiCIE: Unsupervised Semantic Segmentation using Invariance and\n Equivariance in Clustering Open

Jang Hyun Cho, Utkarsh Mall, Kavita Bala, Bharath Hariharan · 2021

We present a new framework for semantic segmentation without annotations via\nclustering. Off-the-shelf clustering methods are limited to curated,\nsingle-label, and object-centric images yet real-world data are dominantly\nuncurated, mult…

Unified Shape and SVBRDF Recovery using Differentiable Monte Carlo Rendering Open

Fujun Luan, Shuang Zhao, Kavita Bala, Zhao Yang Dong · 2021

Reconstructing the shape and appearance of real-world objects using measured 2D images has been a long-standing problem in computer vision. In this paper, we introduce a new analysis-by-synthesis technique capable of producing high-quality…

Insights from a Large-Scale Database of Material Depictions in Paintings Open

Hubert Lin, Mitchell van Zuijlen, Maarten Wijntjes, Sylvia C. Pont, Kavita Bala · 2021

What Can Style Transfer and Paintings Do For Model Robustness? Open

Hubert Lin, Mitchell van Zuijlen, Sylvia C. Pont, Maarten Wijntjes, Kavita Bala · 2020

A common strategy for improving model robustness is through data augmentations. Data augmentations encourage models to learn desired invariances, such as invariance to horizontal flipping or small changes in color. Recent work has shown th…

A Database of Painterly Material Depictions Open

Mitchell van Zuijlen, Hubert Lin, Kavita Bala, Sylvia C. Pont, Maarten Wijntjes · 2020

Painters depict materials by utilizing an implicit knowledge of human material perception. To enable studies of this implicit knowledge, we created a database of paintings annotated with bounding boxes of various depicted materials (e.g., …

Award talks Open

Tzu-Mao Li, Alec Jacobsen, Jeffrey Shaw, Kavita Bala, Elizabeth Baron , et al. · 2020

Award presentation Open

Kavita Bala, Alec Jacobsen, Tzu-Mao Li, Thierry Frey, Jeffrey Shaw , et al. · 2020

Effect of geometric sharpness on translucent material perception Open

Bei Xiao, Shuang Zhao, Ioannis Gkioulekas, Wenyan Bi, Kavita Bala · 2020

When judging the optical properties of a translucent object, humans often look at sharp geometric features such as edges and thin parts. An analysis of the physics of light transport shows that these sharp geometries are necessary for scie…

DeepSemanticHPPC: Hypothesis-based Planning over Uncertain Semantic Point Clouds Open

Yutao Han, Hubert Lin, Jacopo Banfi, Kavita Bala, Mark Campbell · 2020

Planning in unstructured environments is challenging -- it relies on sensing, perception, scene reconstruction, and reasoning about various uncertainties. We propose DeepSemanticHPPC, a novel uncertainty-aware hypothesis-based planner for …

Kavita Bala YOU? Author Swipe