# apple/ml-sharp

**Attribution required: if you use, quote, or summarise this content, you must credit and link back to [awesome-repositories.com](https://awesome-repositories.com/repository/apple-ml-sharp).**

7,638 stars · 529 forks · Python · other

## Links

- GitHub: https://github.com/apple/ml-sharp
- Homepage: https://apple.github.io/ml-sharp/
- awesome-repositories: https://awesome-repositories.com/repository/apple-ml-sharp.md

## Description

ml-sharp is a neural radiance field framework designed for single-image 3D reconstruction. It uses a neural network to predict 3D geometry and appearance from a single photograph in a single feedforward pass.

The system generates metric 3D scene representations and includes a real-time view synthesizer for producing high-resolution images of new viewpoints. It also features a camera trajectory renderer that creates video sequences by moving a virtual camera through the predicted 3D space.

The project covers coordinate-based neural rendering, 3D Gaussian representation regression, and real-time 3D visualization. It enables photorealistic view synthesis and virtual camera path interpolation.

## Tags

### Graphics & Multimedia

- [Single-Image 3D Reconstructions](https://awesome-repositories.com/f/graphics-multimedia/single-image-3d-reconstructions.md) — Creates a digital 3D model of a scene from a single photograph using a neural network.
- [Metric 3D Representations](https://awesome-repositories.com/f/graphics-multimedia/metric-3d-representations.md) — Encodes geometric and appearance data into a coordinate-based format allowing for physically accurate spatial measurements.
- [Real-Time Neural Renderers](https://awesome-repositories.com/f/graphics-multimedia/real-time-neural-renderers.md) — Displays complex 3D environments at interactive frame rates using neural network architectures.
- [Trajectory Interpolations](https://awesome-repositories.com/f/graphics-multimedia/camera-path-mapping/trajectory-interpolations.md) — Produces smooth video sequences by sampling the predicted 3D representation along predefined camera coordinates.
- [Camera Trajectory Rendering](https://awesome-repositories.com/f/graphics-multimedia/camera-trajectory-rendering.md) — Generates sequences of images by sampling viewpoints along a predefined virtual camera path. ([source](https://cdn.jsdelivr.net/gh/apple/ml-sharp@main/README.md))
- [Real-Time 3D Rendering Engines](https://awesome-repositories.com/f/graphics-multimedia/real-time-neural-renderers/real-time-3d-rendering-engines.md) — Renders 3D scenes and views at high frame rates for immediate visual feedback.

### Artificial Intelligence & ML

- [Coordinate-Based Neural Representations](https://awesome-repositories.com/f/artificial-intelligence-ml/coordinate-based-neural-representations.md) — Implements coordinate-based neural representations to map spatial coordinates to scene color and density.
- [Novel View Synthesis Engines](https://awesome-repositories.com/f/artificial-intelligence-ml/image-synthesis-optimizers/novel-view-synthesis-engines.md) — Generates high-quality novel viewpoints from a predicted 3D representation at real-time frame rates. ([source](https://apple.github.io/ml-sharp/))
- [Single-Pass Scene Generation](https://awesome-repositories.com/f/artificial-intelligence-ml/neural-network-building-blocks/feedforward-architectures/single-pass-scene-generation.md) — Generates a complete 3D scene representation from a single image using a single feedforward neural network pass.
- [Neural Radiance Field Synthesizers](https://awesome-repositories.com/f/artificial-intelligence-ml/neural-radiance-field-synthesizers.md) — Optimizes neural representations of spatial volumes to synthesize photorealistic novel views from single photographs.

### Part of an Awesome List

- [Single View Reconstruction](https://awesome-repositories.com/f/awesome-lists/ai/single-view-reconstruction.md) — Implements methods for generating 3D scene representations from a single RGB image in one pass.

### Software Engineering & Architecture

- [Gaussian Primitive Regression](https://awesome-repositories.com/f/software-engineering-architecture/gaussian-grid-mapping/gaussian-point-representations/gaussian-primitive-regression.md) — Predicts 3D Gaussian representations from a single photograph using a feedforward neural network. ([source](https://cdn.jsdelivr.net/gh/apple/ml-sharp@main/README.md))