Source code for 2021 ICCV paper "In-the-Wild Single Camera 3D Reconstruction Through Moving Water Surfaces"

Last update: Dec 06, 2022

Overview

In-the-Wild Single Camera 3D Reconstruction
Through Moving Water Surfaces

This is the PyTorch implementation for 2021 ICCV paper "In-the-Wild Single Camera 3D Reconstruction Through Moving Water Surfaces"

Project Page | Paper | Supplemental Material

In-the-Wild Single Camera 3D Reconstruction Through Moving Water Surfaces
Jinhui Xiong, Wolfgang Heidrich
KAUST
ICCV 2021 (Oral)

We propose a differentiable framework to estimate underwater scene geometry along with the time-varying water surface. The inputs to our model are a video sequence captured by a fixed camera. Dense correspondence from each frame to a world reference frame (selected from the input sequences) is pre-computed, ensuring the reconstruction is performed in a unified coordinate system. We feed the flow fields, together with initialized water surfaces and scene geometry (all are initialized as planar surfaces), into the framework, which incorporates ray casting, Snell’s law and multi-view triangulation. The gradients of the specially designed losses with respect to water surfaces and scene geometry are back-propagated, and all parameters are simultaneously optimized. The final result is a quality reconstruction of the underwater scene, along with an estimate of the time-varying water-air interface. The data shown here was captured in a public fountain environment.

Prerequisite

The code was tested with python>=3.7 & PyTorch>=1.3 & cuda>=10.0 on Nvidia RTX 2080 Ti
Minor change on the code if there is compatibility issue. It needs around 10 GB GPU memory.

Setup

conda create -n moving_water python=3.7
conda activate moving_water

conda install pytorch torchvision -c pytorch
conda install -c conda-forge opencv scikit-image
conda install -c anaconda scipy

Run the code

Please go to example folder, download the cached coefficient matrices (there are three matrices for each example) and execute:

python3 run.py

Citation

@inproceedings{xiong2021inthewild,
  title={In-the-Wild Single Camera 3D Reconstruction Through Moving Water Surfaces},
  author={Jinhui Xiong and Wolfgang Heidrich},
  year={2021},
  booktitle={ICCV}
}

Contact

Please contact Jinhui Xiong [email protected] if you have any question or comment.

Source code for 2021 ICCV paper "In-the-Wild Single Camera 3D Reconstruction Through Moving Water Surfaces"

Related tags

Overview

In-the-Wild Single Camera 3D Reconstruction
Through Moving Water Surfaces

Project Page | Paper | Supplemental Material

Prerequisite

Setup

Run the code

Citation

Contact

Owner

Certified Patch Robustness via Smoothed Vision Transformers

GenshinMapAutoMarkTools - Tools To add/delete/refresh resources mark in Genshin Impact Map

Disease Informed Neural Networks (DINNs) — neural networks capable of learning how diseases spread, forecasting their progression, and finding their unique parameters (e.g. death rate).

Nested cross-validation is necessary to avoid biased model performance in embedded feature selection in high-dimensional data with tiny sample sizes

PPO Lagrangian in JAX

The official implementation of paper Siamese Transformer Pyramid Networks for Real-Time UAV Tracking, accepted by WACV22

Method for facial emotion recognition compitition of Xunfei and Datawhale .

Binary Passage Retriever (BPR) - an efficient passage retriever for open-domain question answering

Multi-Objective Loss Balancing for Physics-Informed Deep Learning

Open CV - Convert a picture to look like a cartoon sketch in python

Kaggle G2Net Gravitational Wave Detection : 2nd place solution

Official code for "Focal Self-attention for Local-Global Interactions in Vision Transformers"

The official PyTorch implementation for the paper "sMGC: A Complex-Valued Graph Convolutional Network via Magnetic Laplacian for Directed Graphs".

Labelbox is the fastest way to annotate data to build and ship artificial intelligence applications

A ssl analyzer which could analyzer target domain's certificate.

Tello Drone Trajectory Tracking

Fast SHAP value computation for interpreting tree-based models

Learning from Synthetic Data with Fine-grained Attributes for Person Re-Identification

Automatic self-diagnosis program (python required)Automatic self-diagnosis program (python required)

RRL: Resnet as representation for Reinforcement Learning