[CVPR 2021] Scan2Cap: Context-aware Dense Captioning in RGB-D Scans

Overview

Scan2Cap: Context-aware Dense Captioning in RGB-D Scans

Introduction

We introduce the task of dense captioning in 3D scans from commodity RGB-D sensors. As input, we assume a point cloud of a 3D scene; the expected output is the bounding boxes along with the descriptions for the underlying objects. To address the 3D object detection and description problems, we propose Scan2Cap, an end-to-end trained method, to detect objects in the input scene and describe them in natural language. We use an attention mechanism that generates descriptive tokens while referring to the related components in the local context. To reflect object relations (i.e. relative spatial relations) in the generated captions, we use a message passing graph module to facilitate learning object relation features. Our method can effectively localize and describe 3D objects in scenes from the ScanRefer dataset, outperforming 2D baseline methods by a significant margin (27.61% [email protected] improvement).

Please also check out the project website here.

For additional detail, please see the Scan2Cap paper:
"Scan2Cap: Context-aware Dense Captioning in RGB-D Scans"
by Dave Zhenyu Chen, Ali Gholami, Matthias Nießner and Angel X. Chang
from Technical University of Munich and Simon Fraser University.

Data

ScanRefer

If you would like to access to the ScanRefer dataset, please fill out this form. Once your request is accepted, you will receive an email with the download link.

Note: In addition to language annotations in ScanRefer dataset, you also need to access the original ScanNet dataset. Please refer to the ScanNet Instructions for more details.

Download the dataset by simply executing the wget command:

wget <download_link>

Scan2CAD

As learning the relative object orientations in the relational graph requires CAD model alignment annotations in Scan2CAD, please refer to the Scan2CAD official release (you need ~8MB on your disk). Once the data is downloaded, extract the zip file under data/ and change the path to Scan2CAD annotations (CONF.PATH.SCAN2CAD) in lib/config.py . As Scan2CAD doesn't cover all instances in ScanRefer, please download the mapping file and place it under CONF.PATH.SCAN2CAD. Parsing the raw Scan2CAD annotations by the following command:

python scripts/Scan2CAD_to_ScanNet.py

Setup

Please execute the following command to install PyTorch 1.8:

conda install pytorch==1.8.0 torchvision==0.9.0 torchaudio==0.8.0 cudatoolkit=10.2 -c pytorch

Install the necessary packages listed out in requirements.txt:

pip install -r requirements.txt

And don't forget to refer to Pytorch Geometric to install the graph support.

After all packages are properly installed, please run the following commands to compile the CUDA modules for the PointNet++ backbone:

cd lib/pointnet2
python setup.py install

Before moving on to the next step, please don't forget to set the project root path to the CONF.PATH.BASE in lib/config.py.

Data preparation

  1. Download the ScanRefer dataset and unzip it under data/ - You might want to run python scripts/organize_scanrefer.py to organize the data a bit.
  2. Download the preprocessed GLoVE embeddings (~990MB) and put them under data/.
  3. Download the ScanNetV2 dataset and put (or link) scans/ under (or to) data/scannet/scans/ (Please follow the ScanNet Instructions for downloading the ScanNet dataset).

After this step, there should be folders containing the ScanNet scene data under the data/scannet/scans/ with names like scene0000_00

  1. Pre-process ScanNet data. A folder named scannet_data/ will be generated under data/scannet/ after running the following command. Roughly 3.8GB free space is needed for this step:
cd data/scannet/
python batch_load_scannet_data.py

After this step, you can check if the processed scene data is valid by running:

python visualize.py --scene_id scene0000_00
  1. (Optional) Pre-process the multiview features from ENet.

    a. Download the ENet pretrained weights (1.4MB) and put it under data/

    b. Download and decompress the extracted ScanNet frames (~13GB).

    c. Change the data paths in config.py marked with TODO accordingly.

    d. Extract the ENet features:

    python scripts/compute_multiview_features.py

    e. Project ENet features from ScanNet frames to point clouds; you need ~36GB to store the generated HDF5 database:

    python scripts/project_multiview_features.py --maxpool

    You can check if the projections make sense by projecting the semantic labels from image to the target point cloud by:

    python scripts/project_multiview_labels.py --scene_id scene0000_00 --maxpool

Usage

End-to-End training for 3D dense captioning

Run the following script to start the end-to-end training of Scan2Cap model using the multiview features and normals. For more training options, please run scripts/train.py -h:

python scripts/train.py --use_multiview --use_normal --use_topdown --use_relation --use_orientation --num_graph_steps 2 --num_locals 10 --batch_size 12 --epoch 50

The trained model as well as the intermediate results will be dumped into outputs/ . For evaluating the model (@0.5IoU), please run the following script and change the accordingly, and note that arguments must match the ones for training:

python scripts/eval.py --folder <output_folder> --use_multiview --use_normal --use_topdown --use_relation --num_graph_steps 2 --num_locals 10 --eval_caption --min_iou 0.5

Evaluating the detection performance:

python scripts/eval.py --folder <output_folder> --use_multiview --use_normal --use_topdown --use_relation --num_graph_steps 2 --num_locals 10 --eval_detection

You can even evaluate the pretraiend object detection backbone:

python scripts/eval.py --folder <output_folder> --use_multiview --use_normal --use_topdown --use_relation --num_graph_steps 2 --num_locals 10 --eval_detection --eval_pretrained

If you want to visualize the results, please run this script to generate bounding boxes and descriptions for scene to outputs/ :

python scripts/visualize.py --folder <output_folder> --scene_id <scene_id> --use_multiview --use_normal --use_topdown --use_relation --num_graph_steps 2 --num_locals 10

Note that you need to run python scripts/export_scannet_axis_aligned_mesh.py first to generate axis-aligned ScanNet mesh files.

3D dense captioning with ground truth bounding boxes

For experimenting the captioning performance with ground truth bounding boxes, you need to extract the box features with a pre-trained extractor. The pretrained ones are already in pretrained, but if you want to train a new one from scratch, run the following script:

python scripts/train_maskvotenet.py --batch_size 8 --epoch 200 --lr 1e-3 --wd 0 --use_multiview --use_normal

The pretrained model will be stored under outputs/ . Before we proceed, you need to move the to pretrained/ and change the name of the folder to XYZ_MULTIVIEW_NORMAL_MASKS_VOTENET, which must reflect the features while training, e.g. MULTIVIEW -> --use_multiview.

After that, let's run the following script to extract the features for the ground truth bounding boxes. Note that the feature options must match the ones in the previous steps:

python scripts/extract_gt_features.py --batch_size 16 --epoch 100 --use_multiview --use_normal --train --val

The extracted features will be stored as a HDF5 database under /gt_ _features . You need ~610MB space on your disk.

Now the box features are ready - we're good to go! Next step: run the following command to start training the dense captioning pipeline with the extraced ground truth box features:

python scripts/train_pretrained.py --mode gt --batch_size 32 --use_topdown --use_relation --use_orientation --num_graph_steps 2 --num_locals 10

For evaluating the model, run the following command:

python scripts/eval_pretrained.py --folder <ouptut_folder> --mode gt --use_topdown --use_relation --use_orientation --num_graph_steps 2 --num_locals 10 

3D dense captioning with pre-trained VoteNet bounding boxes

If you would like to play around with the pre-trained VoteNet bounding boxes, you can directly use the pre-trained VoteNet in pretrained. After picking the model you like, run the following command to extract the bounding boxes and associated box features:

python scripts/extract_votenet_features.py --batch_size 16 --epoch 100 --use_multiview --use_normal --train --val

Now the box features are ready. Next step: run the following command to start training the dense captioning pipeline with the extraced VoteNet boxes:

python scripts/train_pretrained.py --mode votenet --batch_size 32 --use_topdown --use_relation --use_orientation --num_graph_steps 2 --num_locals 10

For evaluating the model, run the following command:

python scripts/eval_pretrained.py --folder <ouptut_folder> --mode votenet --use_topdown --use_relation --use_orientation --num_graph_steps 2 --num_locals 10 

Experiments on ReferIt3D

Yes, of course you can use the ReferIt3D dataset for training and evaluation. Simply download ReferIt3D dataset and unzip it under data, then run the following command to convert it to ScanRefer format:

python scripts/organize_referit3d.py

Then you can simply specify the dataset you would like to use by --dataset ReferIt3D in the aforementioned steps. Have fun!

2D Experiments

Please refer to Scan2Cad-2D for more information.

Citation

If you found our work helpful, please kindly cite our paper via:

@inproceedings{chen2021scan2cap,
  title={Scan2Cap: Context-aware Dense Captioning in RGB-D Scans},
  author={Chen, Zhenyu and Gholami, Ali and Nie{\ss}ner, Matthias and Chang, Angel X},
  booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  pages={3193--3203},
  year={2021}
}

License

Scan2Cap is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.

Copyright (c) 2021 Dave Zhenyu Chen, Ali Gholami, Matthias Nießner, Angel X. Chang

Owner
Dave Z. Chen
PhD candidate at TUM
Dave Z. Chen
Official repository for "On Improving Adversarial Transferability of Vision Transformers" (2021)

Improving-Adversarial-Transferability-of-Vision-Transformers Muzammal Naseer, Kanchana Ranasinghe, Salman Khan, Fahad Khan, Fatih Porikli arxiv link A

Muzammal Naseer 47 Dec 02, 2022
Code for classifying international patents based on the text of their titles/abstracts

Patent Classification Goal: To train a machine learning classifier that can automatically classify international patents downloaded from the WIPO webs

Prashanth Rao 1 Nov 08, 2022
Lacmus is a cross-platform application that helps to find people who are lost in the forest using computer vision and neural networks.

lacmus The program for searching through photos from the air of lost people in the forest using Retina Net neural nwtwork. The project is being develo

Lacmus Foundation 168 Dec 27, 2022
PyTorch implementation for Graph Contrastive Learning with Augmentations

Graph Contrastive Learning with Augmentations PyTorch implementation for Graph Contrastive Learning with Augmentations [poster] [appendix] Yuning You*

Shen Lab at Texas A&M University 382 Dec 15, 2022
Contextual Attention Localization for Offline Handwritten Text Recognition

CALText This repository contains the source code for CALText model introduced in "CALText: Contextual Attention Localization for Offline Handwritten T

0 Feb 17, 2022
Face2webtoon - Despite its importance, there are few previous works applying I2I translation to webtoon.

Despite its importance, there are few previous works applying I2I translation to webtoon. I collected dataset from naver webtoon 연애혁명 and tried to transfer human faces to webtoon domain.

이상윤 64 Oct 19, 2022
Implementation of "Deep Implicit Templates for 3D Shape Representation"

Deep Implicit Templates for 3D Shape Representation Zerong Zheng, Tao Yu, Qionghai Dai, Yebin Liu. arXiv 2020. This repository is an implementation fo

Zerong Zheng 144 Dec 07, 2022
Get started learning C# with C# notebooks powered by .NET Interactive and VS Code.

.NET Interactive Notebooks for C# Welcome to the home of .NET interactive notebooks for C#! How to Install Download the .NET Coding Pack for VS Code f

.NET Platform 425 Dec 25, 2022
PyTorch implementation of Neural Combinatorial Optimization with Reinforcement Learning.

neural-combinatorial-rl-pytorch PyTorch implementation of Neural Combinatorial Optimization with Reinforcement Learning. I have implemented the basic

Patrick E. 454 Jan 06, 2023
TensorRT examples (Jetson, Python/C++)(object detection)

TensorRT examples (Jetson, Python/C++)(object detection)

Nobuo Tsukamoto 53 Dec 22, 2022
Framework for abstracting Amiga debuggers and access to AmigaOS libraries and devices.

Framework for abstracting Amiga debuggers. This project provides abstration to control an Amiga remotely using a debugger. The APIs are not yet stable

Roc Vallès 39 Nov 22, 2022
(CVPR 2021) Lifting 2D StyleGAN for 3D-Aware Face Generation

Lifting 2D StyleGAN for 3D-Aware Face Generation Official implementation of paper "Lifting 2D StyleGAN for 3D-Aware Face Generation". Requirements You

Yichun Shi 66 Nov 29, 2022
Learned Token Pruning for Transformers

LTP: Learned Token Pruning for Transformers Check our paper for more details. Installation We follow the same installation procedure as the original H

Sehoon Kim 52 Dec 29, 2022
ROSITA: Enhancing Vision-and-Language Semantic Alignments via Cross- and Intra-modal Knowledge Integration

ROSITA News & Updates (24/08/2021) Release the demo to perform fine-grained semantic alignments using the pretrained ROSITA model. (15/08/2021) Releas

Vision and Language Group@ MIL 48 Dec 23, 2022
Neural Module Network for VQA in Pytorch

Neural Module Network (NMN) for VQA in Pytorch Note: This is NOT an official repository for Neural Module Networks. NMN is a network that is assembled

Harsh Trivedi 111 Nov 24, 2022
Ascend your Jupyter Notebook usage

Jupyter Ascending Sync Jupyter Notebooks from any editor About Jupyter Ascending lets you edit Jupyter notebooks from your favorite editor, then insta

Untitled AI 254 Jan 08, 2023
Miscellaneous and lightweight network tools

Network Tools Collection of miscellaneous and lightweight network tools to simplify daily operations, administration, and troubleshooting of networks.

Nicholas Russo 22 Mar 22, 2022
This project provides the proof of the uniqueness of the equilibrium and the global asymptotic stability.

Delayed-cellular-neural-network This project provides the proof of the uniqueness of the equilibrium and the global asymptotic stability. There is als

4 Apr 28, 2022
A programming language written with python

Kaoft A programming language written with python How to use A simple Hello World: c="Hello World" c Output: "Hello World" Operators: a=12

1 Jan 24, 2022
Consensus score for tripadvisor

ContripScore ContripScore is essentially a score that combines an Internet platform rating and a consensus rating from sentiment analysis (For instanc

Pepe 1 Jan 13, 2022