Neural Scene Graphs for Dynamic Scene (CVPR 2021)

Overview

Neural Scene Graphs for Dynamic Scene (CVPR 2021)

alt text

Project Page | Paper

Julian Ost, Fahim Mannan, Nils Thuerey, Julian Knodt, Felix Heide

Implementation of Neural Scene Graphs, that optimizes multiple radiance fields to represent different objects and a static scene background. Learned representations can be rendered with novel object compositions and views.

Original repository forked from the Implementation of "NeRF: Neural Radiance Fields" by Mildenhall et al.: Original NeRF Implementation, original readme


Getting started

The whole script is currently optimized for the usage with Virtual KITTI 2 Dataset and KITTI

Quick Start

Train a Virtual KITTI 2 Scene

conda create -n neural_scene_graphs --file requirements.txt -c conda-forge -c menpo
conda activate neural_scene_graphs
cd neural-scene-graphs
bash download_virtual_kitti.sh
python main.py --config example_configs/config_vkitti2_Scene06.py
tensorboard --logdir=example_weights/summaries --port=6006

Render a pretrained KITTI Scene from a trained Scene Graph Models

Follow the instructions under data preparation to setup the KITTI dataset.

conda create -n neural_scene_graphs --file requirements.txt -c conda-forge -c menpo
conda activate neural_scene_graphs
cd neural-scene-graphs
bash download_weights_kitti.sh
python main.py --config example_configs/config_kitti_0006_example_render.py
tensorboard --logdir=example_weights/summaries --port=6006

Disclaimer: The codebase is optimized to run on larger GPU servers with a lot of free CPU memory. To test on local and low memory,

  1. Use chunk and netchunk in the config files to limit parallel computed rays and sampling points.

or

  1. resize and retrain with
--training_factor = 'downsampling factor'

or change to the desired factor in your config file.


Data Preperation

KITTI

  1. Get the KITTI MOT dataset, from which you need:
    1. Left color images
    2. Right color images
    3. GPS/IMU data
    4. Camera Calibration Files
    5. Training labels
  2. Extract everything to ./data/kitti and keep the data structure
  3. Neural Scene Graphs is well tested and published on real front-facing scenarios with only small movements along the camera viewing direction. We therefore prepared selected config files for KITTI Scenes (0001, 0002, 0006)

Virtual KITTI 2

bash ./download_virtual_kitti.sh

Training

To optimize models on a subsequence of Virtual KITTI 2 or KITTI, create the environment, download the data set (1.2) and optimize the (pre-trained) background and object models together:

conda create -n neural_scene_graphs --file requirements.txt -c conda-forge -c menpo
conda activate neural_scene_graphs

vkitti2 example:

python main.py --config example_configs/config_vkitti2_Scene06.txt
tensorboard --logdir=example_weights/summaries --port=6006

KITTI example:

python main.py --config example_configs/config_kitti_0006_example_train.txt
tensorboard --logdir=example_weights/summaries --port=6006

Rendering a Sequence

Render a pretrained KITTI sequence

bash download_weights_kitti.sh
python main.py --config example_configs/config_kitti_0006_example_render.txt

To render a pre-trained download the weights or use your own model.

bash download_weights_kitti.sh

To make a full render pass over all selected images (between the first and last frame) run the provided config with 'render_only=True'.

  • To render only the outputs of the static background node use 'bckg_only=True'
  • for all dynamic parts set 'obj_only=True' & 'white_bkgd=True'
python main.py --config example_configs/config_kitti_0006_example_render.txt

Citation

@InProceedings{Ost_2021_CVPR,
    author    = {Ost, Julian and Mannan, Fahim and Thuerey, Nils and Knodt, Julian and Heide, Felix},
    title     = {Neural Scene Graphs for Dynamic Scenes},
    booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
    month     = {June},
    year      = {2021},
    pages     = {2856-2865}
}
A simple image/video to Desmos graph converter run locally

Desmos Bezier Renderer A simple image/video to Desmos graph converter run locally Sample Result Setup Install dependencies apt update apt install git

Kevin JY Cui 339 Dec 23, 2022
Official repository of "BasicVSR++: Improving Video Super-Resolution with Enhanced Propagation and Alignment"

BasicVSR_PlusPlus (CVPR 2022) [Paper] [Project Page] [Code] This is the official repository for BasicVSR++. Please feel free to raise issue related to

Kelvin C.K. Chan 227 Jan 01, 2023
TensorFlow implementation of "Variational Inference with Normalizing Flows"

[TensorFlow 2] Variational Inference with Normalizing Flows TensorFlow implementation of "Variational Inference with Normalizing Flows" [1] Concept Co

YeongHyeon Park 7 Jun 08, 2022
naked is a Python tool which allows you to strip a model and only keep what matters for making predictions.

naked is a Python tool which allows you to strip a model and only keep what matters for making predictions. The result is a pure Python function with no third-party dependencies that you can simply c

Max Halford 24 Dec 20, 2022
Harmonic Memory Networks for Graph Completion

HMemNetworks Code and documentation for Harmonic Memory Networks, a series of models for compositionally assembling representations of graph elements

mlalisse 0 Oct 27, 2021
KAPAO is an efficient multi-person human pose estimation model that detects keypoints and poses as objects and fuses the detections to predict human poses.

KAPAO (Keypoints and Poses as Objects) KAPAO is an efficient single-stage multi-person human pose estimation model that models keypoints and poses as

Will McNally 664 Dec 30, 2022
'Aligned mixture of latent dynamical systems' (amLDS) for stimulus decoding probabilistic manifold alignment across animals. P. Herrero-Vidal et al. NeurIPS 2021 code.

Across-animal odor decoding by probabilistic manifold alignment (NeurIPS 2021) This repository is the official implementation of aligned mixture of la

Pedro Herrero-Vidal 3 Jul 12, 2022
Reinforcement Learning for the Blackjack

Reinforcement Learning for Blackjack Author: ZHA Mengyue Math Department of HKUST Problem Statement We study playing Blackjack by reinforcement learni

Dolores 3 Jan 24, 2022
A toolset of Python programs for signal modeling and indentification via sparse semilinear autoregressors.

SPAAR Description A toolset of Python programs for signal modeling via sparse semilinear autoregressors. References Vides, F. (2021). Computing Semili

Fredy Vides 0 Oct 30, 2021
Data-driven reduced order modeling for nonlinear dynamical systems

SSMLearn Data-driven Reduced Order Models for Nonlinear Dynamical Systems This package perform data-driven identification of reduced order model based

Haller Group, Nonlinear Dynamics 27 Dec 13, 2022
Spatial Transformer Nets in TensorFlow/ TensorLayer

MOVED TO HERE Spatial Transformer Networks Spatial Transformer Networks (STN) is a dynamic mechanism that produces transformations of input images (or

Hao 36 Nov 23, 2022
Implements pytorch code for the Accelerated SGD algorithm.

AccSGD This is the code associated with Accelerated SGD algorithm used in the paper On the insufficiency of existing momentum schemes for Stochastic O

205 Jan 02, 2023
Simple object detection app with streamlit

object-detection-app Simple object detection app with streamlit. Upload an image and perform object detection. Adjust the confidence threshold to see

Robin Cole 68 Jan 02, 2023
The 1st Place Solution of the Facebook AI Image Similarity Challenge (ISC21) : Descriptor Track.

ISC21-Descriptor-Track-1st The 1st Place Solution of the Facebook AI Image Similarity Challenge (ISC21) : Descriptor Track. You can check our solution

lyakaap 75 Jan 08, 2023
Deep Reinforced Attention Regression for Partial Sketch Based Image Retrieval.

DARP-SBIR Intro This repository contains the source code implementation for ICDM submission paper Deep Reinforced Attention Regression for Partial Ske

2 Jan 09, 2022
This repository contains code, network definitions and pre-trained models for working on remote sensing images using deep learning

Deep learning for Earth Observation This repository contains code, network definitions and pre-trained models for working on remote sensing images usi

Nicolas Audebert 447 Jan 05, 2023
A dual benchmarking study of visual forgery and visual forensics techniques

A dual benchmarking study of facial forgery and facial forensics In recent years, visual forgery has reached a level of sophistication that humans can

8 Jul 06, 2022
(CVPR 2021) Back-tracing Representative Points for Voting-based 3D Object Detection in Point Clouds

BRNet Introduction This is a release of the code of our paper Back-tracing Representative Points for Voting-based 3D Object Detection in Point Clouds,

86 Oct 05, 2022
Code for ViTAS_Vision Transformer Architecture Search

Vision Transformer Architecture Search This repository open source the code for ViTAS: Vision Transformer Architecture Search. ViTAS aims to search fo

46 Dec 17, 2022
Convert game ISO and archives to CD CHD for emulation on Linux.

tochd Convert game ISO and archives to CD CHD for emulation. Author: Tuncay D. Source: https://github.com/thingsiplay/tochd Releases: https://github.c

Tuncay 20 Jan 02, 2023