Niantic
SDK

Niantic
SDK
enables
developers
to
build
immersive
AR
experiences
that
seamlessly
blend
digital
content
with
the
real
world,
leveraging
real-time
meshing,
semantic
understanding,
and
computer
vision
within
a
versatile,
cross-platform
toolkit.

Trusted
by
40,000
developers
for
cross-platform
development

Create
multi-user,
real-world
AR
experiences

The
Niantic
SDK
provides
advanced
geospatial
services
and
on-device
computer
vision
features,
including
depth,
occlusion,
semantics,
and
real-time
meshing.
Niantic’s Visual Positioning System (VPS)
enables
developers
to
precisely
localize
users
and
anchor
AR
content
with
centimeter-level
accuracy—in
just
seconds.

Key
Features

  • Networking
    APIs:
    Synchronize
    content,
    actions,
    and
    more

  • Shared
    AR
    sessions:
    Support
    for
    up
    to
    10
    simultaneous
    users

  • Peer-to-peer
    messaging:
    Includes
    server
    support

  • Secure
    sessions:
    Built-in
    authentication
    and
    encryption

  • Co-localization
    :
    Shared
    AR
    experiences
    enhanced
    by
    VPS

Real-time
Meshing

Niantic
SDK’s
meshing
feature
rapidly
constructs
a
machine-readable
representation
of
the
physical
world,
enabling
immersive
experiences
that
seamlessly
interact
with
real-world
environments.
Leverage
realistic
depth
,
occlusion
,
physics
,
and
object placement
to
build
dynamic
applications.
With
our
scanning
SDK,
visualize
digitized
factory
equipment
directly
on
the
factory
floor,
ensuring
seamless
integration
with
existing
machinery.
Enhance
safety
and
efficiency
by
using
depth
and
meshing
to
prevent
interference
between
people
and
equipment.

  • Real-time
    depth
    estimation
    and
    occlusion

  • Session-persistent
    meshing

  • Cross-platform
    functionality

Semantic
Understanding

Niantic's
Semantic
Segmentation
APIs
enable
digital
objects
to
interact
accurately
with
real-world
surfaces,
ensuring
they
appear—or
remain
hidden—where
they
naturally
should.

Within
the
Niantic
SDK,
these
APIs
use
computer
vision
to
instantly
identify
key
environmental
elements—such
as
ground,
sky,
water,
and
buildings—enabling
real-time
understanding
that
shapes
how
virtual
content
interacts
seamlessly
and
realistically
within
a
space.

With
semantic
awareness,
developers
can
recognize
and
classify
real-world
elements
instantly,
enabling
intelligent
placement
and
interaction
of
virtual
content
in
any
setting.

Categories
include:

  • Water,
    sky,
    ground
    (natural
    and
    artificial)

  • Buildings

  • Foliage

  • Advanced
    object
    detection
    with
    over
    200
    categories

Connect
every
moment.
Across
context-aware
AR

Get Started with Niantic SDKExplore our Pricing