InstantMesh

Image-to-Mesh

Generates 3D meshes from single images using deep learning models

InstantMesh: Efficient 3D Mesh Generation from a Single Image with Sparse-view Large Reconstruction Models

GitHub

3k stars
49 watching
358 forks
Language: Python
last commit: 10 days ago
Linked from 1 awesome list


Backlinks from these awesome lists:

Related projects:

Repository Description Stars
wjakob/instant-meshes Software generates interactive field-aligned meshes from input data. 5,167
nvlabs/instant-ngp A software toolkit for training and rendering neural graphics primitives 16,033
mrforexample/comfyui-3d-pack An extensive suite of nodes for processing 3D inputs and generating images/videos in ComfyUI using cutting-edge algorithms and models. 2,371
ashawkey/stable-dreamfusion Generates 3D content from text using a combination of neural networks and image synthesis. 8,296
one-2-3-45/one-2-3-45 An open-source project that enables the generation of 3D mesh models from single images in under a minute. 1,563
facebookresearch/pytorch3d A deep learning library for 3D data processing and computer vision research using PyTorch 8,806
cumulo-autumn/streamdiffusion A pipeline-level solution for real-time interactive image generation using diffusion-based techniques 9,736
huggingface/diffusers A PyTorch-based library for training and using state-of-the-art diffusion models to generate images, audio, and 3D structures 26,223
tencentarc/gfpgan An algorithm for restoring damaged or obscured faces in images 35,898
gkjohnson/three-mesh-bvh An optimization library for raycasting and spatial queries against 3D meshes in web-based graphics applications 2,545
ericlbuehler/mistral.rs A fast and flexible LLM inference platform supporting various models and devices 4,466
huggingface/accelerate A tool to simplify training and deployment of PyTorch models on various devices and configurations 7,947
openai/point-e Generates 3D point clouds from text prompts or images. 6,539
tencent/pocketflow A framework that automatically compresses and accelerates deep learning models to make them suitable for mobile devices with limited computational resources. 2,788
hujie-frank/senet An implementation of the Squeeze-and-Excitation Networks architecture in Caffe 3,394