Such lensless cameras have numerous vision applications in areas such as Augmented Reality (AR)/Virtual Reality (VR), security, smart wearables and robotics where cost, form-factor, and weight are major constraints, say researchers from IIT Madras and Rice University.

Due to the absence of this focusing element, the lensless camera captures a multiplexed or globally blurred measurement of the scene.

Taking out a lens can lead to the miniaturization of a camera. Researchers globally are trying to find substitutes for lenses.

In 2016, Professor Ashok Veeraraghavan’s lab at Rice University registered success in making a lensless camera.

They were able to develop a low-cost and low-weight ultra-thin lensless camera. The function of lenses is to focus the incoming light.

In these newly developed lensless cameras, a thin optical mask was placed just in front of the sensor at a distance of approximately 1 mm.

However, because of the absence of focusing elements, the lensless camera captures blurred images restricting their commercial use.

IIT Madras and Rice University researchers have now developed a computational solution to this problem.

The team of researchers from IIT Madras and Rice University developed a de-blurring algorithm, which can correct the blurred images taken from a lensless camera.

The findings of the research by Rice University and IIT Madras were presented as a paper in the prestigious IEEE international conference on Computer Vision and an extended version appeared in IEEE Transactions on Pattern Analysis and Machine Intelligence.

The team of researchers at IIT Madras were led by Dr. Kaushik Mitra who is Assistant Professor at Department of Electrical Engineering.

The team from Rice University was led by Professor Ashok Veeraraghavan. The members in the reasearch team from Rice University comprised Dr. Vivek Boominathan and Mr. Jasper Tan.

Speaking about the work done by researchers from IIT Madras and Rice University, Dr. Kaushik Mitra said existing algorithms to deblur images based on traditional optimization schemes yield low-resolution ‘noisy images.’

The team from IIT Madras and Rice University used Deep Learning to develop a reconstruction algorithm called ‘FlatNet’ for lensless cameras which resulted in significant improvement over traditional optimization-based algorithms.

Also read ‘Mahindra University offers new courses in MTech, BA and BBA. Click here to know how to apply‘

FlatNet was tested on various real and challenging scenarios and was found to be effective in de-blurring images captured by the lensless camera, said Dr. Kaushik.

Speaking more about the research by team from IIT Madras and Rice University, Dr. Kaushik said lensless imaging is a new technology and its true potential in solving imaging/vision problems has not been exploited completely.

Therefore, we are working on designing newer and better lensless cameras using data-driven techniques, devising efficient algorithms for doing inference on lensless captures and looking into interesting and important applications like endoscopy and smart surveillance, among other areas, where one can fully realize the benefits of lensless imaging, said Dr. Kaushik.

The work taken up by team from IIT Madras and Rice University was funded by National Science Foundation (NSF) CAREER and NSF EXPEDITIONS, U.S., Neural Engineering System Design (NESD) – Defense Advanced Research Projects Agency (DARPA), U.S., National Institutes of Health (NIH) Grant, U.S., and Qualcomm Innovation Fellowship India 2020.

Background for this research
For centuries the basic architecture of a camera has remained the same – a lens focuses the incoming light rays from the scene to the sensor, thereby recording a 2D projection of the scene.

Although this conventional imaging technique has been used ubiquitously, it has its own limitations such as bulky form-factor, weight, and costly optics.

To overcome these limitations, lensless imaging systems are being developed in recent years.

This results in a lensless camera that is only a few millimeters thin, lightweight and cost-effective.

However, because of the absence of a lens, the lensless camera captures a highly multiplexed or blurred version of the scene, which needs to be reconstructed computationally.

In this work, the IIT Madras researchers exploited deep learning to improve this computational aspect of lensless cameras, which will further help in the proliferation of this new and exciting technology into mainstream applications.

Read More – Most toughest exams in India

The schedule to submit applications for JEE Advanced 2025 has been announced along with that of AAT 2025 registration,

Application process for AAT starts after result declaration of JEE Advanced. This year too, the trend is no different.

Who will conduct AAT 2025?

AAT 2025 will be conducted by IIT Kanpur and is expected to see a participation in impressive numbers. The same institution is conducting JEE Advanced 2025.

Details about the exam are available on the official website mentioned above. Students who pass AAT 2025 will be able to study BArch in IIT Roorkee, IIT Kharagpur and IIT (BHU) Varnasi.

Who can take up AAT 2025 registration?

Students who have passed JEE Advanced 2025 with required qualifying marks can take up AAT 2025 registration. Applying for JEE Advanced requires a pass in JEE Mains.

Candidates who have passed plus two with maths, physics and chemistry as subjects will be able to take up JEE Mains registration. The process to take up JEE Advanced AAT 2025 registration is online.

1. The URL has to be typed into the browser and the webpage has to be allowed to download.

2. Once the website is available, students should click the link for JEE Advanced AAT 2025 registration and enter JEE Advanced 2025 registration number, their date of birth, mobile number and email address.

3. Post providing the above details, applicants will be asked if they are interested in AAT. Students have to answer ‘Yes’ to take up JEE Advanced AAT 2025 registration.

4. Candidates have to provide the required information and choose the centers where they wish to write the exam and submit the form.

5. They will receive message indicating successful completion of JEE Advanced AAT 2025 registration.

The message has to be downloaded and a printout of it has to be taken and preserved for use in future. This could be of use during the admission process.

Website for JEE Advanced 2025/AAT 2025 Registration is Here

Exam pattern

Candidates who have completed JEE Advanced AAT 2025 registration must also know the exam pattern if they are to score good marks.

Those who have taken up AAT 2025 registration can take up the exam which will be held in offline mode, as a pen and paper mode test.

Candidates will have three hours time to answer all the questions. The medium of the test is English.

The sections in the question paper are – Imagination and aesthetic sensitivity, three dimensional perception, Geometrical drawing, Freehand drawing and Architectural Awareness.

Syllabus for AAT 2025

The next thing to do after completing AAT 2025 registration is focus on preparing for the test.

The subjects to be studied while preparing for AAT 2025 are mentioned below. Candidates can also refer the official website for more information on syllabus when the registration for the exam begins:

Geometrical Drawing

Exercises in geometrical drawing containing lines, angles, triangles, quadrilaterals, polygons, circles, etc. Study of plan (top view), elevation (front or side views) of simple solid objects like prisms, cones, cylinders, cubes, splayed surface holders, etc.

Freehand Drawing

This would comprise of simple drawing depicting the total object in its right form and proportion, surface texture, relative location and details of its component parts in appropriate scale.

Common domestic or day-to-day life usable objects like furniture, equipment, etc., from memory.

Three dimension perception

Understanding and appreciation of three-dimensional forms with building elements, colour, volume and orientation. Visualization through structuring objects in memory.

Architectural Awareness

General interest and awareness of famous architectural creations – both national and international, places and personalities (architects, designers, etc.) in the related domain.

Imagination and Aesthetic Sensitivity

Composition exercise with given elements. Context mapping.

Creativity check through innovative uncommon test with familiar objects. Sense of colour grouping or application.

The medium of the test is English. The sections in the question paper are – Imagination and aesthetic sensitivity, three dimensional perception, Geometrical drawing, Freehand drawing and Architectural Awareness.

The admit cards obtained for JEE Advanced 2025 can also be used to gain entry into the test centers for AAT 2024.

Point to remember

Candidates can visit the official website of JEE Advanced exam for more information on JEE Advanced AAT 2025 registration and other related topics.

The students have to quickly take up the AAT 2025 registration as the time left would be very short.

Like JEE Advanced exam where the registration is open for a longer duration, that of AAT 2025 registration is open for only a short period.

The details about AAT 2025 registration provided above are for general understanding purpose of the students.

There could be some changes in the exam, students can visit the official website of the exam at regular intervals to receive updates.

More information could be provided as the time for AAT 2025 registration would commence, till that time, students can refer other sources also.

Also Read – NIRF 2024 Top 20 Architecture Colleges, Great For Studies