difix

**Difix3D+: Improving 3D Reconstructions with Single-Step Diffusion Models** CVPR 2025 (Oral) Code** | **Project Page** | **Paper** 📣📣 The commercially available model (Fixer) is now released here 📣📣 Use the Difix Model Please visit the Difix3D repository to access all relevant files and code needed to use Difix Description: Difix is a single-step image diffusion model trained to enhance and remove artifacts in rendered novel views caused by underconstrained regions of 3D representation. The technology behind Difix is based on the concepts outlined in the paper titled DIFIX3D+: Improving 3D Reconstructions with Single-Step Diffusion Models. Difix has two operation modes: Offline mode: Used during the reconstruction phase to clean up pseudo-training views that are rendered from the reconstruction and then distill them back into 3D. This greatly enhances underconstrained regions and improves the overall 3D representation quality. Online mode: Acts as a neural enhancer during inference, effectively removing residual artifacts arising from imperfect 3D supervision and the limited capacity of current reconstruction models. Difix is an all-encompassing solution, a single model compatible for both NeRF and 3DGS representations. This model is ready for research and development/non-commercial use only.** Model Developer:** NVIDIA Model Versions:** difix Deployment Geography:** Global License/Terms of Use: The use of the model and code is governed by the NVIDIA License. Additional Information: LICENSE.md · stabilityai/sd-turbo at main Use Case: Difix is intended for Physical AI developers looking to enhance and improve their Neural Reconstruction pipelines. The model takes an image as an input and outputs a fixed image Release Date:** Github: June 2025 Model Architecture Architecture Type**: UNet Network Architecture**: A latent diffusion-based UNet coupled with a variational autoencoder (VAE). Input Input Type(s)**: Image Input Format(s)**: Red, Green, Blue (RGB) Input Param