single-image-reconstruction

Here are 10 public repositories matching this topic...

Language: All

Filter by language

All 10 Python 7 Jupyter Notebook 1 MATLAB 1

cleardusk / 3DDFA_V2

The official PyTorch implementation of Towards Fast, Accurate and Stable 3D Dense Face Alignment, ECCV 2020.

computer-vision pytorch alignment 3d 3d-face face-alignment 3dmm 3d-face-alignment eccv onnx 3d-landmarks eccv-2020 single-image-reconstruction

Updated Feb 2, 2024
Python

soubhiksanyal / RingNet

Star 862

Learning to Regress 3D Face Shape and Expression from an Image without 3D Supervision

python computer-vision deep-learning tensorflow face flame 3d-models face-reconstruction triplet-loss 3d-data 2d-3d 3d-mesh benchmark-datasets 3d-face-reconstruction morphable-model 3d-landmarks flame-model single-image-reconstruction ringnet

Updated Mar 24, 2023
Python

astra-vision / MonoScene

Star 783

[CVPR 2022] "MonoScene: Monocular 3D Semantic Scene Completion": 3D Semantic Occupancy Prediction from a single image

computer-vision deep-learning pytorch mayavi monocular occupancy-prediction semantic-scene-understanding 2d-to-3d nyu-depth-v2 semantic-scene-completion semantic-kitti single-image-reconstruction kitti-360 cvpr2022 cvpr22

Updated Apr 6, 2024
Python

astra-vision / SceneRF

Star 378

[ICCV 2023] Official implementation of "SceneRF: Self-Supervised Monocular 3D Scene Reconstruction with Radiance Fields"

deep-learning pytorch nerf 3d-reconstruction depth-estimation self-supervised self-supervised-learning scene-reconstruction pytorch-lightning single-image-reconstruction neural-radiance-fields

Updated Mar 3, 2024
Python

PeizhiYan / flame-head-tracker

Star 115

FLAME head tracker for single image reconstruction and monocular video tracking. [Note: This tracker operates offline and is not intended for real-time applications.]

flame 3d-face 3dmm face-tracking 3d-face-reconstruction face-tracker single-image-reconstruction head-avatar 3d-head 3d-head-reconstruction

Updated Aug 3, 2025
Jupyter Notebook

soubhiksanyal / now_evaluation

Star 114

This is the official repository for evaluation on the NoW Benchmark Dataset. The goal of the NoW benchmark is to introduce a standard evaluation metric to measure the accuracy and robustness of 3D face reconstruction methods from a single image under variations in viewing angle, lighting, and common occlusions.