This is the Linux app named ML Sharp whose latest release can be downloaded as ml-sharpsourcecode.tar.gz. It can be run online in the free hosting provider OnWorks for workstations.
Download and run online this app named ML Sharp with OnWorks for free.
Follow these instructions in order to run this app:
- 1. Downloaded this application in your PC.
- 2. Enter in our file manager https://www.onworks.net/myfiles.php?username=XXXXX with the username that you want.
- 3. Upload this application in such filemanager.
- 4. Start the OnWorks Linux online or Windows online emulator or MACOS online emulator from this website.
- 5. From the OnWorks Linux OS you have just started, goto our file manager https://www.onworks.net/myfiles.php?username=XXXXX with the username that you want.
- 6. Download the application, install it and run it.
SCREENSHOTS
Ad
ML Sharp
DESCRIPTION
ML Sharp is a research code release that turns a single 2D photograph into a photorealistic 3D representation that can be rendered from nearby viewpoints. Instead of requiring multi-view input, it predicts the parameters of a 3D Gaussian scene representation directly from one image using a single forward pass through a neural network. The core idea is speed: the 3D representation is produced in under a second on a standard GPU, and then the resulting scene can be rendered in real time to generate new views interactively. The representation is metric, meaning it supports camera movements with an absolute scale rather than only relative depth cues, which is useful for consistent viewpoint changes and downstream spatial tasks. The project is structured for reproducibility, with code and assets aimed at demonstrating view synthesis quality, sharp details, and fine structures when rendering high-resolution images.
Features
- Single-image to 3D Gaussian scene regression
- Sub-second scene creation on a standard GPU
- Real-time rendering for nearby novel views
- Metric-scale representation for consistent camera motion
- High-resolution photorealistic output with fine detail preservation
- Research-oriented codebase for evaluation and reproducibility
Programming Language
Python
Categories
This is an application that can also be fetched from https://sourceforge.net/projects/ml-sharp.mirror/. It has been hosted in OnWorks in order to be run online in an easiest way from one of our free Operative Systems.
