Appraise, an app that aims to provide a gamified real-world item scanner and collecting experience for Android with a modern Material 3 interface. (Current release: v0.0.1-poc)
Used Gemini 3.1 Pro Preview for most of the boilerplate and initial implementation.
Appraise v0.0.1-poc — The Visual Extraction Engine!
The devlog before this covers most of the details… But to sum it up I am starting a new project! The project is called appraise and as the name suggests, it allows you to appraise things around you, I have major plans for this going forward, read more if your interested!
What did you make?
Before I can turn real life into a game, I had to figure out how to make real-life objects actually look pristine and cool. This v0.0.1 Proof-of-Concept is entirely focused on building a premium visual extraction pipeline.
The Extraction Engine: I hooked up Google ML Kit via Play Services to instantly identify and extract the primary object from a live CameraX preview.
Strict Subject Isolation: AI models can be messy and highlight background artifacts. To fix this, I wrote a blazing-fast, custom Kotlin Flood-Fill algorithm that isolates the single largest contiguous visual mass, completely deleting stray pixels and enforcing a one-object-only rule.
Dynamic VFX Compositing: The UI isn’t just an image slapped on a background! Using GPU-accelerated BlurMaskFilter passes and SRC_IN blending, a massive neon glow visually bleeds through the edges of the object.
What was challenging?
Getting the ML Kit segmentation to run without crashing on modern hardware! I had to specifically migrate the core ML pipeline to properly support the new Android 15 and 16KB memory page hardware architectures to prevent legacy native crashes on newer Pixel devices. Also, figuring out how to run a custom flood-fill algorithm and heavy GPU compositing math instantly on the main UI thread without causing massive lag was a huge headache.
What are you proud of?
I am super proud of the edge light-wrapping math. Normally, when you cut an object out of a photo using AI, it looks like a cheap, jagged Photoshop job. By getting the background neon glow to wrap and bleed through the edges of the AI mask, it perfectly hides real-world light reflections and jagged cuts. It actually makes mundane things look like premium collectible items!
Download Link: You can grab the debug APK directly from GitHub here: https://github.com/Animesh-Varma/Appraise/releases/download/v0.0.1-poc/Appraise-v0.0.1-poc-debug.apk
I’m taking a quick breather from my other projects to drop a brand new, wildly ambitious app! Meet Appraise!!
Appraise is a gamified camera app that turns the mundane real world into a massive, globally deduplicated collectible RPG. Point your camera at everyday objects to instantly extract them from reality and add them to your personal digital catalogue with procedurally generated stats and rarities! It isn’t just a scanner; it’s a collaborative project aiming to build a global encyclopedia of everyday things, complete with a creator economy for artists who claim and illustrate the items you find (not the AI slop you find these days)!
What did I make?
Before I can turn real life into a game, I had to figure out how to make real-life objects actually look pristine and cool. This v0.0.1 Proof-of-Concept is entirely focused on building a premium visual extraction pipeline:
This project is my absolute first foray into something that actually requires me to handle complex backends and APIs, so it’s going to be a massive learning curve!
Repo is public, but APKs are GitHub-only for now while I build out the backend and iron out the bugs!
[BTW the attached screenshots give a quick look at the final edge-blending math!]
Log in to leave a comment