There are 5 repositories under scene-understanding topic.
Lightweight models for real-time semantic segmentationon PyTorch (include SQNet, LinkNet, SegNet, UNet, ENet, ERFNet, EDANet, ESPNet, ESPNetv2, LEDNet, ESNet, FSSNet, CGNet, DABNet, Fast-SCNN, ContextNet, FPENet, etc.)
A list of recent papers, libraries and datasets about 3D shape/scene analysis (by topics, updating).
🔥🔥Official Repository for Multi-Human-Parsing (MHP)🔥🔥
PyTorch implementation of multi-task learning architectures, incl. MTI-Net (ECCV2020).
😎 A list of papers for scene understanding papers in computer vision.
[ECCV'20] Structured3D: A Large Photo-realistic Dataset for Structured 3D Modeling
Implementation of CVPR'20 Oral: Total3DUnderstanding: Joint Layout, Object Pose and Mesh Reconstruction for Indoor Scenes from a Single Image
[AAAI 2020] Towards Ghost-free Shadow Removal via Dual Hierarchical Aggregation Network and Shadow Matting GAN
[ECCV'18] 3DMV: Joint 3D-Multi-View Prediction for 3D Semantic Scene Segmentation
A paper list of RGBD semantic segmentation (processing)
Implementation of CVPR'21: RfD-Net: Point Scene Understanding by Semantic Instance Reconstruction
FPConv: Learning Local Flattening for Point Convolution, CVPR 2020
VSGNet:Spatial Attention Network for Detecting Human Object Interactions Using Graph Convolutions.
Predict Vehicle collision moments before it happens in Carla!. CNN and LSTM hybrid architecture is used to understand a series of images.
This is the dataset and code release of the OpenRooms Dataset. For more information, please refer to our webpage below. Thanks a lot for your interest in our research!
Learning to Reconstruct 3D Non-Cuboid Room Layout from a Single RGB Image
Semantic Scene Completion
[CVPR 2021] Exploiting Edge-Oriented Reasoning for 3D Point-based Scene Graph Analysis (official pytorch implementation)
Implement some state-of-the-art methods of Semantic Scene Completion (SSC) task in PyTorch.  3D Sketch-aware Semantic Scene Completion via Semi-supervised Structure Prior (CVPR 2020)
This repository contains the dataset and the source code for the detection of visual relationships with the Logic Tensor Networks framework.
Attend Infer Repeat (AIR) in PyTorch
[CVPR'22] Official PyTorch Implementation of Collaborative Transformers for Grounded Situation Recognition
[BMVC'21] Official PyTorch Implementation of Grounded Situation Recognition with Transformers
PyTorch implementation of "Pyramid Scene Parsing Network".
[CVPR 2022] Understanding 3D Object Articulation in Internet Videos
Collect data sets and research papers in the field of 3D computer vision tasks with implemented repositories.
[ECCV Workshop'20] General Room Layout Estimation Track in Holistic 3D Vision Challenge
[IJCAI 2022] Spatiality-guided Transformer for 3D Dense Captioning on Point Clouds (official pytorch implementation)
This study investigates the performance effect of using recurrent neural networks (RNNs) for semantic segmentation of urban scene images, to generate a semantic output map with refined edges. We proposed three deep neural network architectures using recurrent neural networks and evaluated them on the Cityscapes dataset. All three proposed architectures outperformed the baseline and shown improvement in classifying edges. Additionally, we showed a new method for using RNN for any prior semantic segmentation network that makes use of skip connections. PyTorch was the selected framework for conducting this study.
This is the code for our ICCV'19 paper on cross-modal learning and retrieval.
A Brief Tutorial on LiDAR data visualisation and classification
Oskar Natan and Jun Miura, "Towards Compact Autonomous Driving Perception With Balanced Learning and Multi-Sensor Fusion", IEEE Transactions on Intelligent Transportation Systems.
Oskar Natan and Jun Miura, "Semantic Segmentation and Depth Estimation with RGB and DVS Sensor Fusion for Multi-view Driving Perception", IAPR Asian Conference on Pattern Recognition, 2021.