Saturday, July 26, 2025

Creating liberating content

File photo: Commerce and industry minister Piyush Goyal (Picture credit:

Union minister Piyush Goyal (left) and Britain’s secretary of state

Related News

File photo: Commerce and industry minister Piyush Goyal (Picture credit: PTI) Commerce and industry minister Piyush Goyal on Saturday said that discussions with the United States on the proposed bilateral

Union minister Piyush Goyal (left) and Britain’s secretary of state for business and trade, Jonathan Reynolds, shake hands after they signed the free trade agreement. (Picture credit: AP) India has

Sanjiv Puri (left), ITC (TOI) Leading FMCG conglomerate ITC Ltd. plans to invest Rs 20,000 crore across its business verticals over the medium term, spanning the next five to six

NEW DELHI: Union commerce and industry minister Piyush Goyal on Saturday hailed the newly signed free trade agreement with the United Kingdom and said that the deal was signed on

Edelweiss mutual fund CEO Radhika Gupta emphasized the importance of adopting a more well-rounded approach to personal finances, one that extends beyond the conventional emphasis on saving and long-term investing.“My

While treatment costs in India are low, so are the medical insurance premiums. (AI image) New Delhi: Low medical insurance premiums, affordable treatment costs and high quality healthcare facilities at

Trending News

NEW DELHI: Union commerce and industry minister Piyush Goyal on Saturday hailed the newly signed free trade agreement with the United Kingdom and said that the deal was signed on

While treatment costs in India are low, so are the medical insurance premiums. (AI image) New Delhi: Low medical insurance premiums, affordable treatment costs and high quality healthcare facilities at

MUMBAI: There is no proposal to allow corporates – either directly or through NBFCs – to obtain banking licences, RBI governor Sanjay Malhotra said on Friday, citing “an inherent conflict

MUMBAI: SBI Cards reported a 6.4% decline in net profit to Rs. 556 crore for the June quarter, compared with Rs. 594 crore a year earlier, as higher impairment losses

This is a representative AI image (Pic credit: Lexica) NEW DELHI: Scotch and British gin makers may have been successful in gaining lower duty access to the Indian market, but

BENGALURU: Bengaluru-based Yali Capital closed its debut deep tech-focused fund at Rs 893 crore, exceeding its original Rs 500 crore target and Rs 310 crore greenshoe option. The Sebi-registered Category

New AI model with synthetic images boosts mixed reality object detection: IISc

Word Count: 662 | Estimated Reading Time: 4 minutes


New AI model with synthetic images boosts mixed reality object detection: IISc

BENGALURU: Researchers at the Indian Institute of Science (IISc) have developed an innovative solution to a persistent challenge in Mixed Reality (MR) technology for industrial applications: the need for extensive image datasets to train AI systems.
The team from IISc’s Department of Design and Manufacturing, led by Pradipta Biswas, has demonstrated that diffusion models — a specialised AI approach — can generate synthetic images that significantly improve object detection accuracy while dramatically reducing the need for real-world images.
“In recent years, MR technologies, where digital and physical elements are blended, are increasingly finding applications in manufacturing and maintenance industries. These systems often rely on AI to identify and interact with real-world objects,” IISc said.
However, it added, to train these AI models effectively, a large and diverse collection of images is needed.
Pointing out that gathering such real-world data can be expensive, time-consuming, and sometimes impossible in industrial settings due to safety or access restrictions, IISc said Biswas and team have found a creative solution: synthetic image generation.
Instead of collecting thousands of real photographs, they used a special kind of AI approach, called a diffusion model, to generate realistic images.
They took images of real objects – such as parts of a pneumatic cylinder – and blended them with different background scenes where object detection has previously struggled. As per IISc, this helps the model “see” the object in a wide variety of settings, making it better at recognising the object in real life.
“The team tested this method against two other common techniques: traditional editing and GAN (Generative Adversarial Network). The diffusion-based approach led to much higher accuracy in detecting objects, even though it used fewer images. Specifically, it improved the detection performance by 11% while using 67% fewer images than the traditional methods,” IISc said.
Additionally, the team has created an easy-to-use interface so that others can generate their own synthetic data without deep technical knowledge, IISc said, adding that this makes it a powerful tool for improving machine learning models in MR applications where data is limited.





Source link

Most Popular Articles

Sign In

Welcome ! Log into Your Account