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

🏅 Top 5% in 제2회 연구개발특구 인공지능 경진대회 AI SPARK 챌린지

Joint detection and tracking model named DEFT, or ``Detection Embeddings for Tracking.

RMNA: A Neighbor Aggregation-Based Knowledge Graph Representation Learning Model Using Rule Mining

An implementation of Deep Forest 2021.2.1.

Explainability for Vision Transformers (in PyTorch)

ML model to classify between cats and dogs

A pre-trained model with multi-exit transformer architecture.

Data Augmentation with Variational Autoencoders

Imagededup - 😎 Finding duplicate images made easy

Vision Transformer and MLP-Mixer Architectures

Joint Unsupervised Learning (JULE) of Deep Representations and Image Clusters.

Implementation of Gans

An Industrial Grade Federated Learning Framework

Implementation of "GNNAutoScale: Scalable and Expressive Graph Neural Networks via Historical Embeddings" in PyTorch

Code for the paper "Benchmarking and Analyzing Point Cloud Classification under Corruptions"

efficient neural audio synthesis in the waveform domain

Adaptive FNO transformer - official Pytorch implementation

The NEOSSat is a dual-mission microsatellite designed to detect potentially hazardous Earth-orbit-crossing asteroids and track objects that reside in deep space

Management Dashboard for Torchserve

Minimal PyTorch implementation of Generative Latent Optimization from the paper "Optimizing the Latent Space of Generative Networks"