OpenMMLab Series

  1. Python MMCV. OpenMMLab foundational Python library for computer vision research
  2. PyTorch MMDetection. OpenMMLab Detection Toolbox, a codebase that was used by MMDet team, who won the COCO Detection 2018 Challenge
  3. PyTorch MMEditing. A unified toolbox for popular inpainting, matting, super-resolution, and generation tasks. The toolbox includes various popular image super-resolution methods such as SRCNN, SRResNet, SRGAN, ESRGAN, EDVR, etc.
  4. PyTorch MMDetection3D. The next generation toolbox for general 3D detection. Support multi-modality/single-modality detectors out of box.
  5. PyTorch MMAction2. A full-fledge toolbox for human action understanding. It covers popular methods such as TSN, I3D, SlowFast, SSN, etc.
  6. PyTorch MMClassification. A toolbox that contains various backbones and pretrained models for image classification.
  7. PyTorch MMSegmentation. A toolbox that supports various semantic segmentation methods.
  8. PyTorch MMPose. The swift knife for pose estimation.
  9. PyTorch MMTracking. A toolbox that include various methods for video object detection, single object tracking, and multiple object tracking.

LiteFlowNet Series

  1. Caffe LiteFlowNet3: Resolving Correspondence Ambiguity for More Accurate Optical Flow Estimation, ECCV 2020. LiteFlowNet3 is built upon our previous work LiteFlowNet2 (TPAMI 2020) with the incorporation of cost volume modulation (CM) and flow field deformation (FD) for improving the flow accuracy further
  2. Caffe LiteFlowNet2: Revisiting Data Fidelity and Regularization, TPAMI 2020. Runtime is 2.2 times faster than LiteFlowNet with improved performance
  3. Caffe LiteFlowNet: A Lightweight Convolutional Neural Network for Optical Flow Estimation, CVPR 2018. Over 30 times smaller in model size, and 1.36 times faster in speed than FlowNet2

Restoration and Processing

  1. PyTorch Cross-Scale Internal Graph Neural Network for Image Super-Resolution, NeurIPS 2020
  2. PyTorch Zero-Reference Deep Curve Estimation for Low-Light Image Enhancement, CVPR 2020
  3. PyTorch Deep Network Interpolation for Continuous Imagery Effect Transition, CVPR 2019
  4. PyTorch ESRGAN: Enhanced Super-Resolution Generative Adversarial Networks, ECCV PIRM Workshop 2018. With this model, we won the first place in PIRM2018-SR competition (region 3) and got the best perceptual index
  5. Torch EnhanceGAN: Aesthetic-Driven Image Enhancement by Adversarial Learning, ACM MM 2018
  6. TensorFlow RL-Restore: Crafting a Toolchain for Image Restoration by Deep Reinforcement Learning, CVPR 2018
  7. Torch, PyTorch SFT-GAN: Recovering Realistic Texture in Image Super-resolution by Deep Spatial Feature Transform, CVPR 2018
  8. Caffe Deep Cascaded Bi-Network for Face Hallucination, ECCV 2016
  9. Caffe MSG-Net: Depth Map Super Resolution by Deep Multi-Scale Guidance, ECCV 2016
  10. Caffe FSRCNN: Accelerating the Super-Resolution Convolutional Neural Network, ECCV 2016
  11. PyTorch DS-Net: Deep Specialized Network for Illuminant Estimation, ECCV 2016
  12. Caffe ARCNN: Compression Artifacts Reduction by a Deep Convolutional Network, ICCV 2015
  13. Caffe SRCNN: Learning a Deep Convolutional Network for Image Super-Resolution, ECCV 2014. The first convolutional neural network for single image super-resolution

Editing and Manipulation

  1. PyTorch Unsupervised 3D Shape Reconstruction from 2D Image GANs, ICLR 2021 Oral
  2. PyTorch Deep Generative Prior, ECCV 2020
  3. PyTorch TSIT: A Simple and Versatile Framework for Image-to-Image Translation, ECCV 2020
  4. PyTorch Self-Supervised Scene De-occlusion, CVPR 2020 Oral
  5. PyTorch TransMoMo: Invariance-Driven Unsupervised Video Motion Retargeting, CVPR 2020
  6. PyTorch RealnessGAN: Real or Not Real, that is the Question, ICLR 2020
  7. PyTorch Delving Deep Into Hybrid Annotations for 3D Human Recovery in the Wild, ICCV 2019
  8. PyTorch One-shot Face Reenactment, BMVC 2019
  9. PyTorch Dense Intrinsic Appearance Flow for Human Pose Transfer, CVPR 2019
  10. PyTorch Deep Flow-Guided Video Inpainting, CVPR 2019
  11. PyTorch ReenactGAN: Learning to Reenact Faces via Boundary Transfer, ECCV 2018
  12. Torch FashionGAN: Be Your Own Prada: Fashion Synthesis with Structural Coherence, ICCV 2017

Detection, Segmentation, and Recognition

  1. PyTorch MessyTable: Instance Association in Multiple Camera Views, ECCV 2020
  2. PyTorch Robust Multi-Modality Multi-Object Tracking, ICCV 2019

Learning

  1. PyTorch OpenSelfSup - Self-Supervised Learning Toolbox and Benchmark, OpenSelfSup integrates various self-supervised tasks including classification, joint clustering and feature learning, contrastive learning, tasks with a memory bank, etc.
  2. PyTorch Knowledge Distillation Meets Self-Supervision, ECCV 2020
  3. PyTorch Inter-Region Affinity Distillation for Road Marking Segmentation, CVPR 2020
  4. PyTorch Learning Lightweight Lane Detection CNNs by Self Attention Distillation, ICCV 2019
  5. PyTorch Self-Supervised Learning via Conditional Motion Propagation, CVPR 2019
  6. PyTorch Learning to Steer by Mimicking Features from Heterogeneous Auxiliary Networks, AAAI 2019 Oral
  7. Caffe Mix-and-Match Tuning for Self-Supervised Semantic Segmentation, AAAI 2018
  8. Caffe Learning Deep Representation for Imbalanced Classification, CVPR 2016

Face Analysis

  1. PyTorch Learning to Cluster Faces on an Affinity Graph, CVPR 2019 Oral
  2. PyTorch Consensus-Driven Propagation in Massive Unlabeled Data for Face Recognition, ECCV 2018
  3. PyTorch Pose-Robust Face Recognition via Deep Residual Equivariant Mapping, CVPR 2018
  4. MATLAB Face Alignment by Coarse-to-Fine Shape Searching, ICCV 2015
  5. MATLAB Facial Landmark Detection by Deep Multi-task Learning, ECCV 2014

Visual Surveillance

  1. Caffe Slicing Convolutional Neural Network for Crowd Video Understanding, CVPR 2016
  2. Caffe Deeply Learned Attributes for Crowded Scene Understanding, CVPR 2015
  3. MATLAB Scene-Independent Group Profiling in Crowd, CVPR 2014