The Fifth Elephant 2025 Annual Conference CfP

The Fifth Elephant 2025 Annual Conference CfP

Speak at The Fifth Elephant 2025 Annual Conference

Shubham Tripathi

@shubham_tripathi

Infographics image generation for e-commerce

Submitted May 31, 2025

Abstract

An Infographic is a product image on Product Display Page (PDP) of an e-commerce website such as target.com, highlighting key features of the product in the image itself reducing the need to scroll down to read product specifications. Displaying the highlights of a product directly on images is shown to drive higher demand and increased guest conversion due to speeded up purchase decision process.

Infographic creation at Target has been completely manual process and suffers from very low coverage for products including first and third party brands. In addition, the design of the infographics is tightly controlled by creative teams and is extremely subtle, leading to limitations of existing tools to support any automations within infographics space.

In this session, I will talk about a patent pending solution to generate infographics at scale for any brand using design template, text generation and vision computing. Specifically, I will talk about the design elements within infographic template, GenAI based text generation, product image segmentation and simulation to obtain the optimal product crop for infographics.

Key Takeaways

  • Understand the design requirements for a general infographic image
  • Look at LLM based feature (text) generation given product description
  • Optimally crop the product image using object segmentation and simulation
  • Understand architecture to handle generic template design

Audience

  • Creative Designers
  • Image processing / Computer Vision experts
  • Developers / Data Scientists building multi-modal pipelines

Presentation Outline

  • Introduction (2 mins)
  • Design elements of Infographics (3 mins)
    • Know about the key design elements
    • Understand key idea that is used in this solution
  • Generating Text with LLM (3 mins)
    • Generating Attribute + Run-On
  • Product Image (12 mins)
    • Automated segmentation of primary and lifestyle images
    • Optimal crop of product based on simulation
  • Architecture and Process Flow (5 min)
    • General pipeline to handle text and image processing within generic template
    • Future work

Bio

Shubham Tripathi is a data science professional with over 10 years of experience in retail and aerospace industry. He holds 4 patents (2 in filing) and many trade secrets within the imaging space. He is currently working as Lead Data Scientist at Target, developing Vision and GenAI based solutions for digital marketing creative design business. Previously, he had worked for Boeing R&D where he invented and led the development of many imaging solutions for improving cabin experience of passengers. He holds BTech and MS in Computer Science from IIIT Hyderabad.

Slide Deck

Infographics-FifthEl-2025.pptx

References

Infographic Example @ Target.com

Comments

{{ gettext('Login to leave a comment') }}

{{ gettext('Post a comment…') }}
{{ gettext('New comment') }}
{{ formTitle }}

{{ errorMsg }}

{{ gettext('No comments posted yet') }}

Hosted by

Jump starting better data engineering and AI futures