Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
(CVPR 2022) TransMVSNet: Global Context-aware Multi-view Stereo Network with Transformers.
| Date | Stars |
|---|---|
| 2026-07-24 | 284 |
| 2026-07-25 | 284 |
| 2026-07-28 | 284 |
| 2026-07-30 | 284 |
| 2026-08-06 | 284 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.00%/day
# (CVPR2022) TransMVSNet: Global Context-aware Multi-view Stereo Network with Transformers ## [Paper](https://openaccess.thecvf.com/content/CVPR2022/papers/Ding_TransMVSNet_Global_Context-Aware_Multi-View_Stereo_Network_With_Transformers_CVPR_2022_paper.pdf) | [Project Page](https://dingyikang.github.io/transmvsnet.github.io/) | [Arxiv](https://arxiv.org/abs/2111.14600/) | [Models](https://drive.google.com/drive/folders/1ZJ9bx9qZENEoXv5i5izKCNszlaCNBMkJ?usp=sharing/) **Tips**: If you meet any problems when reproduce our results, please contact Yikang Ding ([email protected]). We are happy to help you solve the problems and share our experience. ## ⚠ Change log * 09.2022: Add more detailed instruction of how to reproduce the reported results (see [testing-on-dtu](#-testing-on-dtu)). * 09.2022: Fix the bugs in MATLAB evaluation code (remove the debug code). * 09.2022: Fix the bug of default fuse parameters of gipuma, which could have a great impact on the final results. * 09.2022: Update the website link and instruction of installing gipuma, which would affect the fusion quality. ## 📔 Introduction In this paper, we present TransMVSNet, based on our exploration of feature matching in multi-view stereo (MVS). We analogize MVS back to its nature of a feature matching task and therefore propose a powerful Feature Matching Transformer (FMT) to leverage intra- (self-) and inter- (cross-) attention to aggregate long-range context information within and across images. To facilitate a better adaptation of the FMT, we leverage an Adaptive Receptive Field (ARF) module to ensure a smooth transit in scopes of features and bridge different stages with a feature pathway to pass transformed features and gradients across different scales. In addition, we apply pair-wise feature correlation to measure similarity between features, and adopt ambiguity-reducing focal loss to strengthen the supervision. To the best of our knowledge, TransMVSNet is the first attempt to leverage Transformer into the task of MVS. As a result, our method achieves state-of-the-art performance on DTU dataset, Tanks and Temples benchmark, and BlendedMVS dataset.  ## 🔧 Installation Our code is tested with Python==3.6/3.7/3.8, PyTorch==1.6.0/1.7.0/1.9.0, CUDA==10.2 on Ubuntu-18.04 with NVIDIA GeForce RTX 2080Ti. Similar or higher version should work well. To use TransMVSNet, clone this repo: ``` git clone https://github.com/MegviiRobot/TransMVSNet.git cd TransMVSNet ``` We highly recommend using [Anaconda](https://www.anaconda.com/) to manage the python environment: ``` conda create -n transmvsnet python=3.6 conda activate transmvsnet pip install -r requirements.txt ``` <!-- Install pytorch-fast-transformers by: ``` pip install --user pytorch-fast-transformers ``` --> We also recommend using apex, you can install apex from the [official repo](https://www.github.com/nvidia/apex). ## 📦 Data preparation In TransMVSNet, we mainly use [DTU](https://roboimagedata.compute.dtu.dk/), [BlendedMVS](https://github.com/YoYo000/BlendedMVS/) and [Tanks and Temples](https://www.tanksandtemples.org/) to train and evaluate our models. You can prepare the corresponding data by following the instructions below. ### ✔ DTU For DTU training set, you can download the preprocessed [DTU training data](https://drive.google.com/file/d/1eDjh-_bxKKnEuz5h-HXS7EDJn59clx6V/view) and [Depths_raw](https://virutalbuy-public.oss-cn-hangzhou.aliyuncs.com/share/cascade-stereo/CasMVSNet/dtu_data/dtu_train_hr/Depths_raw.zip) (both from [Original MVSNet](https://github.com/YoYo000/MVSNet)), and unzip them to construct a dataset folder like: ``` dtu_training ├── Cameras ├── Depths ├── Depths_raw └── Rectified ``` For DTU testing set, you can download the preprocessed [DTU testing data](https://drive.google.com/open?id=135oKPefcPTsdtLRzoDAQtPpHuoIrpRI_) (from [Original MVSNet](https://github.com/YoYo000/MVSNet)) and unzip it as the test data folder, which should
Excerpt of 11,298 characters
Read on GitHubWould you bet a product on this? Bounded 0–100 and slow moving.
matched fp:c0fa590407b12e83, topic:transformer