Arjun Karpur

Arjun Karpur

Auto-generated profile, based on publicly available information

Arjun Karpur

The University of Texas at Austin

Research Focus & Metrics

Academic Career Length

9Years (2018-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
6 October 2018
Verified
Book Chapter
Closed access
PDF file
XZXingyi Zhou
Xingyi Zhou
AKArjun Karpur
Arjun Karpur
LLLinjie Luo
Linjie Luo
QHQixing Huang
Qixing Huang

6 October 2018
Verified
Book Chapter
Open access
PDF file
XZXingyi Zhou
Xingyi Zhou
AKArjun Karpur
Arjun Karpur
CGChuang Gan
Chuang Gan
LLLinjie Luo
Linjie Luo
QHQixing Huang
Qixing Huang
In this paper, we introduce a novel unsupervised domain adaptation technique for the task of 3D keypoint prediction from a single depth scan or image. Our key idea is to utilize the fact that predictions from different views of the same or similar objects should be consistent with each other. Such view consistency can provide effective regularization for keypoint prediction on unlabeled instances. In addition, we introduce a geometric alignment term to regularize predictions in the target domain. The resulting loss function can be effectively optimized via alternating minimization. We demonstrate the effectiveness of our approach on real datasets and present experimental results showing that our approach is superior to state-of-the-art general-purpose domain adaptation techniques.

22 June 2021 in arXiv
Verified
Preprint
Open access
PDF file
QTQuin Thames
Quin Thames
AKArjun Karpur
Arjun Karpur
WNWade Norris
Wade Norris
FXFangting Xia
Fangting Xia
LPLiviu Panait
Liviu Panait
JSJack Sim
Jack Sim
Understanding the nutritional content of food from visual data is a challenging computer vision problem, with the potential to have a positive and widespread impact on public health. Studies in this area are limited to existing datasets in the field that lack sufficient diversity or labels required for training models with nutritional understanding capability. We introduce Nutrition5k, a novel dataset of 5k diverse, real world food dishes with corresponding video streams, depth images, component weights, and high accuracy nutritional content annotation. We demonstrate the potential of this dataset by training a computer vision algorithm capable of predicting the caloric and macronutrient values of a complex, real world dish at an accuracy that outperforms professional nutritionists. Further we present a baseline for incorporating depth sensor data to improve nutrition predictions. We will publicly release Nutrition5k in the hope that it will accelerate innovation in the space of nutritional understanding.

21 May 2024 in arXiv
Verified
Preprint
Open access
PDF file
HJHanwen Jiang
Hanwen Jiang
AKArjun Karpur
Arjun Karpur
BCBingyi Cao
Bingyi Cao
QHQixing Huang
Qixing Huang
AAAndre Araujo
Andre Araujo
The image matching field has been witnessing a continuous emergence of novel learnable feature matching techniques, with ever-improving performance on conventional benchmarks. However, our investigation shows that despite these gains, their potential for real-world applications is restricted by their limited generalization capabilities to novel image domains. In this paper, we introduce OmniGlue, the first learnable image matcher that is designed with generalization as a core principle. OmniGlue leverages broad knowledge from a vision foundation model to guide the feature matching process, boosting generalization to domains not seen at training time. Additionally, we propose a novel keypoint position-guided attention mechanism which disentangles spatial and appearance information, leading to enhanced matching descriptors. We perform comprehensive experiments on a suite of $7$ datasets with varied image domains, including scene-level, object-centric and aerial images. OmniGlue's novel components lead to relative gains on unseen domains of $20.9\%$ with respect to a directly comparable reference model, while also outperforming the recent LightGlue method by $9.5\%$ relatively.Code and model can be found at https://hwjiang1510.github.io/OmniGlue

26 July 2018 in arXiv
Verified
Preprint
Open access
PDF file
XZXingyi Zhou
Xingyi Zhou
AKArjun Karpur
Arjun Karpur
CGChuang Gan
Chuang Gan
LLLinjie Luo
Linjie Luo
QHQixing Huang
Qixing Huang
In this paper, we introduce a novel unsupervised domain adaptation technique for the task of 3D keypoint prediction from a single depth scan or image. Our key idea is to utilize the fact that predictions from different views of the same or similar objects should be consistent with each other. Such view consistency can provide effective regularization for keypoint prediction on unlabeled instances. In addition, we introduce a geometric alignment term to regularize predictions in the target domain. The resulting loss function can be effectively optimized via alternating minimization. We demonstrate the effectiveness of our approach on real datasets and present experimental results showing that our approach is superior to state-of-the-art general-purpose domain adaptation techniques.