Resource hub

Category

Background Remover

How NSS Background Remover works and why it runs entirely on your device — the client-side AI pipeline, straight-alpha export, on-device upscaling, and the engineering decisions behind a free tool with no uploads.

15 articles

  1. Capability detection choosing WebGPU or WebAssembly, with measured inference timings and a fallback path

    Background Remover · May 25, 2026

    WebGPU vs WASM for client-side ML: what actually changed our inference speed

    WebGPU is faster; WASM is universal. Here is how a real tool uses both, and the measured difference it makes.

    NSS Background Remover

  2. Before and after: tangled per-tool queues versus one canonical queue with isolated per-job workers

    Background Remover · May 23, 2026

    When patches compound, rebuild: the queue and worker overhaul

    The real story of a compounding-patch trap, the decision to rebuild the approach, and the lesson about when patching becomes the problem.

    NSS Background Remover

  3. NSS Background Remover: on-device AI pipeline from image to straight-alpha PNG, no upload

    Background Remover · May 21, 2026

    NSS Background Remover: AI-powered, in-browser background removal — free forever, no signup

    A launch article on why NSS Background Remover exists, how in-browser AI changes the privacy equation, and what straight-alpha export means for professional design workflows.

    NSS Background Remover

  4. Straight versus premultiplied alpha compositing math and the resulting clean edge versus dark halo

    Background Remover · May 21, 2026

    Straight alpha vs premultiplied alpha: the export detail that breaks other tools

    The single most common reason a free cutout looks wrong in professional software, explained with the actual math and what we do differently.

    NSS Background Remover

  5. Five-stage in-browser background removal pipeline from decode to straight-alpha export

    Background Remover · May 20, 2026

    How in-browser background removal works, end to end

    For developers wondering whether client-side ML is viable for a real tool: the actual stages, in order, with the real runtime and the real export detail.

    NSS Background Remover

  6. Diagram contrasting a server-upload background remover with the NSS fully on-device pipeline

    Background Remover · May 19, 2026

    Why our background remover never uploads your image — and what that protects

    Privacy that is structural rather than a policy promise: how fully client-side inference removes the server from the picture, and the engineering bill we paid for it.

    NSS Background Remover

Browse every topic in the resource hub