InstPIFu
Scene Reconstruction
This project aims to develop a method for high-fidelity single-view holistic reconstruction of indoor scenes from a single image.
repository of "Towards High-Fidelity Single-view Holistic Reconstruction of Indoor Scenes" ECCV2022
106 stars
7 watching
9 forks
Language: Jupyter Notebook
last commit: 6 months ago Related projects:
| Repository | Description | Stars |
|---|---|---|
| gap-lab-cuhk-sz/total3dunderstanding | An implementation of a 3D scene reconstruction method from a single image using computer vision and machine learning techniques | 424 |
 zhijieshen-bjtu/dopnet | Estimates room layouts from indoor panoramic images by disentangling orthogonal planes and accounting for cross-scale distortion | 48 |
 hoffsupes/structured-light-laser-stripe-reconstruction | Automatically reconstructs 3D depth information from images of a laser stripe on an object | 45 |
 sunset1995/panoplane360 | A Python framework for reconstructing 3D indoor panoramas from single images using divide and conquer methods | 53 |
 gitcvfb/cvr | Reconstructs high-quality video frames from two adjacent rolling shutter camera frames | 31 |
 opengvlab/internvideo | Develops general video foundation models and related datasets for multimodal understanding and generation through generative and discriminative learning. | 1,467 |
 golnazghiasi/lrr | Code and models for reconstructing and refining images in semantic segmentation using Laplacian Pyramid techniques. | 59 |
 zouchuhang/layoutnet | A deep learning implementation of a 3D room layout reconstruction method from a single RGB image | 419 |
 cyang0515/noncuboidroom | A deep learning project that aims to reconstruct 3D room layouts from single RGB images | 103 |
 svip-lab/planarreconstruction | A PyTorch implementation of a deep learning-based approach to piece-wise planar 3D reconstruction from single images. | 364 |
 cdoersch/vae_tutorial | An open-source implementation of Variational Autoencoders and Conditional Variational Autoencoders for image reconstruction tasks | 503 |
 hongwenzhang/pymaf | Reconstructs human 3D models from monocular images using a feedback loop to improve pose and shape estimation | 600 |
 jefffessler/mirt | A collection of algorithms and code for image reconstruction and related inverse problems. | 173 |
 aminshabani/extreme-indoor-sfm | This project provides a software framework for creating indoor panoramas without visual overlaps, using structure from motion techniques. | 35 |
 infiziert90/getnative | Determines the native resolution of upscaled material, typically anime, by applying various image processing algorithms. | 224 |