HackStack

Project Info

ReAbode

Devpost

Inspiration

As college students who recently moved away from home, we each faced the same struggle of turning a bare, unfamiliar apartment into a space that truly felt like ours. We wanted our rooms to reflect our personalities, but designing within a student budget and without a clear vision made it challenging. We often found ourselves asking: “What furniture fits this space?” “Will this color scheme actually look good?” “Can I afford this aesthetic?” These questions inspired us to build a tool that bridges vision and practicality. Our inspiration came from the shared frustration of browsing endlessly through Pinterest boards or IKEA catalogs, trying to imagine how each piece would fit into our unique rooms. We wanted to make the process of interior design visual, personal, and budget-friendly, even for people with no design background.

What it does

Our project is an AI-powered Room Blueprint and Recommendation System that helps users design their spaces with confidence and creativity. Users upload photos of their rooms from one or multiple angles. The backend analyzes the images to identify the room type, dimensions, and color scheme. A recommendation engine matches these details to curated IKEA products, taking into account style preferences, color palettes, and budget. The user receives personalized furniture recommendations with direct purchase links and a generated room blueprint showing how the pieces can fit together. This combination of computer vision and product matching helps turn vague inspiration into actionable design choices. What We Learned We learned how to combine computer vision, machine learning, and structured product data into a cohesive user experience. Beyond the technical skills, we discovered the importance of usability and accessibility—powerful technology only matters if people can easily use it to improve their daily lives. Next Steps Our next steps focus on expanding and enhancing the experience: Pinterest Integration: Allow users to import mood boards and inspiration photos directly as style references. Generative AI Visualization: Use generative models to simulate redesigned rooms and preview how selected furniture would look. Multi-Store Expansion: Add support for other furniture retailers and local stores to provide more variety and price flexibility. AR Preview: Enable users to walk through their redesigned space in augmented reality to visualize scale and layout in real time. Closing Thoughts This project began as a way to make our new apartments feel like home, but it has grown into something that could help anyone design a space that reflects who they are. By blending AI, design, and accessibility, we aim to make interior design more personal, affordable, and visual—one room at a time.

Analysis

Compare with all teams

View

Metric

Figures cover GitHub contributors during the hackathon window. A co-authored commit counts in full for each author, so per-member totals add up to more than the whole-team figures.

Technology

Found in codeClaimed only
  • CSSIn code
  • FastAPIIn code
  • JavaScriptIn code
  • Next.jsIn code
  • PythonIn code
  • ReactIn code
  • Tailwind CSSIn code
  • TypeScriptIn code
  • Google GeminiClaimed

8 of 9 appear in the indexed code. 1 claimed on Devpost could not be matched to code, which may simply mean the tool leaves no trace in the repository.

AI coding agents

No AI coding agent signals were found in this repository.

Detected from committed agent config files and commit authorship. Absence of a signal is not proof an agent was unused.

Codebase size

Source size

4.9 MB

Source files

46

Counts recognized source files only; vendored directories, binaries and lockfiles are excluded, so this is smaller than the repository on disk.

0 stars