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

Model Serving Made Easy

TCube generates rich and fluent narratives that describes the characteristics, trends, and anomalies of any time-series data (domain-agnostic) using the transfer learning capabilities of PLMs.

The Noise Contrastive Estimation for softmax output written in Pytorch

Tesla Light Show xLights Guide With python

Make differentially private training of transformers easy for everyone

Linescanning - Package for (pre)processing of anatomical and (linescanning) fMRI data

🛠️ Tools for Transformers compression using Lightning ⚡

ICML 21 - Voice2Series: Reprogramming Acoustic Models for Time Series Classification

CKD - Collaborative Knowledge Distillation for Heterogeneous Information Network Embedding

SMCA replication There are no extra compiled components in SMCA DETR and package dependencies are minimal

Training data extraction on GPT-2

The PyTorch implementation of Directed Graph Contrastive Learning (DiGCL), NeurIPS-2021

This initial strategy was developed specifically for larger pools and is based on taking a moving average and deriving Bollinger Bands to create a projected active liquidity range.

Implementation of the Point Transformer layer, in Pytorch

Generative Modelling of BRDF Textures from Flash Images [SIGGRAPH Asia, 2021]

BankNote-Net: Open dataset and encoder model for assistive currency recognition

Using pretrained GROVER to extract the atomic fingerprints from molecule

A no-BS, dead-simple training visualizer for tf-keras

This project uses Template Matching technique for object detecting by detection of template image over base image.

Official repository for Few-shot Image Generation via Cross-domain Correspondence (CVPR '21)