[NeurIPS 2021] Shape from Blur: Recovering Textured 3D Shape and Motion of Fast Moving Objects

Last update: Dec 26, 2022

Overview

[NeurIPS 2021] Shape from Blur: Recovering Textured 3D Shape and Motion of Fast Moving Objects

YouTube | arXiv

Prerequisites

Kaolin is available here: https://github.com/NVIDIAGameWorks/kaolin

Running

The code can be easily run by:

python optimize.py

Running with your inputs:

python optimize.py --im examples/vol_im.png --bgr examples/vol_bgr.png
python optimize.py --im examples/aerobie_im.png --bgr examples/aerobie_bgr.png
python optimize.py --im examples/pen_im.png --bgr examples/pen_bgr.png

The results will be written to the output folder.

Reference

If you use this repository, please cite the following publication:

@misc{sfb,
  title = {Shape from Blur: Recovering Textured 3D Shape and Motion of Fast Moving Objects},
  author = {Denys Rozumnyi and Martin R. Oswald and Vittorio Ferrari and Marc Pollefeys},
  booktitle = {NeurIPS},
  month = {Dec},
  year = {2021}
}

You might also like...

Pop-Out Motion: 3D-Aware Image Deformation via Learning the Shape Laplacian (CVPR 2022)

Pop-Out Motion Pop-Out Motion: 3D-Aware Image Deformation via Learning the Shape Laplacian (CVPR 2022) Jihyun Lee*, Minhyuk Sung*, Hyunjin Kim, Tae-Ky

88 Nov 22, 2022

Code for Discriminative Sounding Objects Localization (NeurIPS 2020)

Discriminative Sounding Objects Localization Code for our NeurIPS 2020 paper Discriminative Sounding Objects Localization via Self-supervised Audiovis

51 Dec 11, 2022

A hand tracking demo made with mediapipe where you can control lights with pinching your fingers and moving your hand up/down.

HandTrackingBrightnessControl A hand tracking demo made with mediapipe where you can control lights with pinching your fingers and moving your hand up

19 Feb 12, 2022

Deep Implicit Moving Least-Squares Functions for 3D Reconstruction

DeepMLS: Deep Implicit Moving Least-Squares Functions for 3D Reconstruction This repository contains the implementation of the paper: Deep Implicit Mo

103 Dec 22, 2022

MonoRec: Semi-Supervised Dense Reconstruction in Dynamic Environments from a Single Moving Camera

494 Jan 6, 2023

Moving Object Segmentation in 3D LiDAR Data: A Learning-based Approach Exploiting Sequential Data

LiDAR-MOS: Moving Object Segmentation in 3D LiDAR Data This repo contains the code for our paper: Moving Object Segmentation in 3D LiDAR Data: A Learn

394 Dec 29, 2022

Simulation of moving particles under microscopic imaging

Simulation of moving particles under microscopic imaging Install scipy numpy scikit-image tiffile Run python simulation.py Read result https://imagej

2 Dec 14, 2021

High-performance moving least squares material point method (MLS-MPM) solver.

High-Performance MLS-MPM Solver with Cutting and Coupling (CPIC) (MIT License) A Moving Least Squares Material Point Method with Displacement Disconti

2.2k Dec 31, 2022

Predict multi paths to a moving person depending on his trajectory history.

Multi-future Trajectory Prediction The project is about using the Multiverse model to make possible multible-future trajectory prediction for a seen p

1 Jan 18, 2022

Comments

cannot import name 'total_variation' from 'kornia'

hi!

what an interesting work!

I have some trouble running the test demo. I have downloaded the newest kornia from pip and tried this https://github.com/kornia/kornia/discussions/1290, but still, get the problem. I wonder if you could give your environment requirements to run the test.

thx :)

Traceback (most recent call last):
  File "optimize.py", line 7, in <module>
    from shapefromblur import *
  File "/dev-data/xxx/projects/SfB/ShapeFromBlur-main/shapefromblur.py", line 12, in <module>
    from models.loss import *
  File "/dev-data/xxx/projects/SfB/ShapeFromBlur-main/models/loss.py", line 3, in <module>
    from kornia import total_variation
ImportError: cannot import name 'total_variation' from 'kornia'

opened by Ayxm1412 2

Releases(v1.0)

v1.0(Jul 9, 2021)

Initial release with simple use-case example.
Source code(tar.gz)
Source code(zip)

Owner

Denys Rozumnyi

PhD student at ETH Zurich.

GitHub Repository https://github.com/rozumden/ShapeFromBlur

NAACL'2021: Factual Probing Is [MASK]: Learning vs. Learning to Recall

OptiPrompt This is the PyTorch implementation of the paper Factual Probing Is [MASK]: Learning vs. Learning to Recall. We propose OptiPrompt, a simple

150 Dec 20, 2022

NFNets and Adaptive Gradient Clipping for SGD implemented in PyTorch

PyTorch implementation of Normalizer-Free Networks and SGD - Adaptive Gradient Clipping Paper: https://arxiv.org/abs/2102.06171.pdf Original code: htt

320 Jan 02, 2023

Differentiable Quantum Chemistry (only Differentiable Density Functional Theory and Hartree Fock at the moment)

DQC: Differentiable Quantum Chemistry Differentiable quantum chemistry package. Currently only support differentiable density functional theory (DFT)

75 Dec 02, 2022

Highly comparative time-series analysis

〰️ hctsa 〰️ : highly comparative time-series analysis hctsa is a software package for running highly comparative time-series analysis using Matlab (fu

569 Dec 21, 2022

Tom-the-AI - A compound artificial intelligence software for Linux systems.

Tom the AI (version 0.82) WARNING: This software is not yet ready to use, I'm still setting up the GitHub repository. Should be ready in a few days. T

2 Apr 28, 2022

Pytorch implementation of paper "Efficient Nearest Neighbor Language Models" (EMNLP 2021)

57 Jan 01, 2023

A unified framework for machine learning with time series

Welcome to sktime A unified framework for machine learning with time series We provide specialized time series algorithms and scikit-learn compatible

6k Jan 08, 2023

Minimal diffusion models - Minimal code and simple experiments to play with Denoising Diffusion Probabilistic Models (DDPMs)

Minimal code and simple experiments to play with Denoising Diffusion Probabilist

16 Oct 06, 2022

[NeurIPS 2021] Shape from Blur: Recovering Textured 3D Shape and Motion of Fast Moving Objects

Related tags

Overview

[NeurIPS 2021] Shape from Blur: Recovering Textured 3D Shape and Motion of Fast Moving Objects

YouTube | arXiv

Prerequisites

Running

Reference

You might also like...

Pop-Out Motion: 3D-Aware Image Deformation via Learning the Shape Laplacian (CVPR 2022)

Code for Discriminative Sounding Objects Localization (NeurIPS 2020)

A hand tracking demo made with mediapipe where you can control lights with pinching your fingers and moving your hand up/down.

Deep Implicit Moving Least-Squares Functions for 3D Reconstruction

MonoRec: Semi-Supervised Dense Reconstruction in Dynamic Environments from a Single Moving Camera

Moving Object Segmentation in 3D LiDAR Data: A Learning-based Approach Exploiting Sequential Data

Simulation of moving particles under microscopic imaging

High-performance moving least squares material point method (MLS-MPM) solver.

Predict multi paths to a moving person depending on his trajectory history.

Comments

cannot import name 'total_variation' from 'kornia'

Releases(v1.0)

v1.0(Jul 9, 2021)

Owner

Denys Rozumnyi

NAACL'2021: Factual Probing Is [MASK]: Learning vs. Learning to Recall

NFNets and Adaptive Gradient Clipping for SGD implemented in PyTorch

Differentiable Quantum Chemistry (only Differentiable Density Functional Theory and Hartree Fock at the moment)

Highly comparative time-series analysis

Tom-the-AI - A compound artificial intelligence software for Linux systems.

Pytorch implementation of paper "Efficient Nearest Neighbor Language Models" (EMNLP 2021)

A unified framework for machine learning with time series

Minimal diffusion models - Minimal code and simple experiments to play with Denoising Diffusion Probabilistic Models (DDPMs)

FCOSR: A Simple Anchor-free Rotated Detector for Aerial Object Detection

Multi-task Multi-agent Soft Actor Critic for SMAC

[CVPR'20] TTSR: Learning Texture Transformer Network for Image Super-Resolution

Implementation of SSMF: Shifting Seasonal Matrix Factorization

Uses Open AI Gym environment to create autonomous cryptocurrency bot to trade cryptocurrencies.

Locally Differentially Private Distributed Deep Learning via Knowledge Distillation (LDP-DL)

Code for the Paper: Conditional Variational Capsule Network for Open Set Recognition

Code for Ditto: Building Digital Twins of Articulated Objects from Interaction

Swin-Transformer is basically a hierarchical Transformer whose representation is computed with shifted windows.

Fine-grained Control of Image Caption Generation with Abstract Scene Graphs

Kaggle G2Net Gravitational Wave Detection : 2nd place solution

Code release for "COTR: Correspondence Transformer for Matching Across Images"