Dishani Lahiri (original) (raw)
Dishani Lahiri I am a 2nd year MS in Computer Vision student (MSCV) in the Robotics Institute at Carnegie Mellon University. I work on computer vision, natural language processing and machine learning. At CMU, I specifically work with 3D reconstruction, scene understanding, andfine-tuning large language models for personalized domain-specific usecases. I am currently advised by Prof. Kris Kitani to build a low-power visual-inertial odometry system forAria AR glasses that can be used reliably in unseen environments as well. During my summer internship at Slingshot AI, I got a chance to work in a very fast-paced environment with high code-quality standards which enriched my research, software engineering, and product skills. I worked on optimizing fine-tuning of personalized text-to-image models (you can see my results on the home page) , improving the results for Generative aging models, and fine-tuning LLaMA2-7B for personalized text style transfer (paper coming soon). I developed an interest in diffusion models and currently aim to work on text-to-video models. Previously I worked on impactful and profitable projects at Samsung R&D Institute, Bangalore. At Samsung, I was a key innovator for the development and deployment of AI Night mode in Samsung Flagship series and the Expert RAW application. I completed my undergraduate studies in ECE from DTU in 2019. My Bachelor's thesis on Neural Caption Generator was advised by Prof. S. Indu, ex-Head of Department, ECE, DTU. Owing to my interest in human activity recognition, I also worked withProf. D.K. Vishwakarma. Email / CV / Bio / Google Scholar / LinkedIn / Github | ![]() |
---|
Projects & Publications
I'm interested in computer vision, natural language processing, and machine learning, especially in building personalized multi-modal solutions for edge devices.
![]() ![]() |
S2RF: Semantically Stylized Radiance Fields Dishani Lahiri*,Neeraj Panse*,Moneish Kumar* ICCV, 2023 Workshop on AI for 3D Content Creation paper |code | webpage We present our method for transferring style from any arbitrary image(s) to object(s) within a 3D scene. Our primary objective is to offer more control in 3D scene stylization, facilitating the creation of customizable and stylized scene images from arbitrary viewpoints. To achieve this, we propose a novel approach that incorporates nearest neighborhood-based loss, allowing for flexible 3D scene reconstruction while effectively capturing intricate style details and ensuring multi-view consistency. |
---|---|---|
![]() ![]() |
Abnormal human action recognition using average energy images Dishani Lahiri*,Chhavi Dhiman,Dinesh Kumar Vishwakarma IEEE, 2017 Conference on Information and Communication Technology (CICT) paper We propose a solution to detect abnormal human actions in the image using Histogram of Oriented Gradients (HoG) as the feature descriptor, Principal Component Analysis (PCA) as the dimensionality-reduction technique, and Support Vector Machine as the ML tool for classification. We also release a dataset for abnormal human activities of fainting, headache, and chest pain. |
Teaching Experience
- Advanced Computer Vision, CMU (TA) | Instructor: Prof. David Held | Fall 2023
This is a new PhD-level course wherein I am involved in preparing and improving the assignments, maintaining the course website, holding Office Hours, and helping students with the theory and code of concepts covered throughout the course. - Machine Learning, CMU (TA) | Instructor: Prof. Matt Gormley | Spring 2023
Preparing and suggesting exam and assignment problems, and material in order to make the course more effective. Holding recitations and office hours for students.
Awards and Recognition
- Winner (most creative use of Github), HackCMU : Awarded for our project, How Do I Look?, using image-to-text and Large Language Models to generate suggestions for attires based on the event
- Samsung Excellence Award (earlier Samsung Citizen Award), Advanced Development Category : Company-wide Award to recognize major contributions towards the R&D in Night Mode for S21 Flagship series
- Standout Performer in Advanced R&D Work : Succeeded in being 1 out of 100 people in Camera Systems Group to receive this award for constant exceptional efforts towards research and implementation
- Samsung Citizen Award, Group Excellence Category : Company-wide Group award to recognize major contributions towards the development of camera usecases in A71-5G device, the first device with SM7250 chipset
- Standout Performer in Advanced R&D Work : Succeeded in being 1 out of 100 people in Camera Systems Group to receive this award for constant exceptional efforts towards research and implementation
- 1H-2020 Project Incentives : Succeeded in being 1 in 2 out of 100 people in Camera Systems Group to receive the incentive in lieu of exceptional performance in critical projects
- Appreciation letter from HRD Ministry of India : For being in top 0.1 percentile scorers in 12th class CBSE examination. HRD Ministry is the Government of India Body formulates the National Policy of Education