hwpengTristin
Computer vision, image/video synthesis, face recognition, person ReID
Sun Yat-sen UniversityGuangzhou, Guangdong, China
Pinned Repositories
Additive-Margin-Softmax
This is the implementation of paper <Additive Margin Softmax for Face Verification>
anygrasp_sdk
ArtiBoost
[CVPR 2022 Oral] ArtiBoost: Boosting Articulated 3D Hand-Object Pose Estimation via Online Exploration and Synthesis
DFD-model
Domain-Private Factor Detachment Network for NIR-VIS Face Recognition
Domain-private-Factor-Detachment-Network
The proposed DFD combines DiRL, CdFD and CAL into an end-to-end framework.
DSVNs-model
We present an effective Disentangled Spectrum Variations Networks (DSVNs) for NIR-VIS HFR. Two key strategies are introduced to the DSVNs: Spectrum-adversarial Discriminative Feature Learning (SaDFL), and Step-wise Spectrum Orthogonal Decomposition (SSOD).
Facial-Expression-Recognition
Facial-Expression-Recognition in TensorFlow. Detecting faces in video and recognize the expression(emotion).
MDNDC-model
We propose Scatter Loss objective function which can bridge the modality gap while preserving the identity information. Secondly, we design a Multiple Deep Networks (MDN) structure for feature extraction, and propose a joint decision strategy called Diversity Combination to adaptively adjust weights of each deep network.
pytorch_refinenet
Pytorch Implementation of Refinenet
transferlearning
Transfer learning / domain adaptation / domain generalization / multi-task learning etc. Papers, codes, datasets, applications, tutorials.-迁移学习
hwpengTristin's Repositories
hwpengTristin/Domain-private-Factor-Detachment-Network
The proposed DFD combines DiRL, CdFD and CAL into an end-to-end framework.
hwpengTristin/transferlearning
Transfer learning / domain adaptation / domain generalization / multi-task learning etc. Papers, codes, datasets, applications, tutorials.-迁移学习
hwpengTristin/ArtiBoost
[CVPR 2022 Oral] ArtiBoost: Boosting Articulated 3D Hand-Object Pose Estimation via Online Exploration and Synthesis
hwpengTristin/assembly101-download-scripts
Python scripts to download Assembly101 from Google Drive
hwpengTristin/cliport
CLIPort: What and Where Pathways for Robotic Manipulation
hwpengTristin/dinov2
PyTorch code and models for the DINOv2 self-supervised learning method.
hwpengTristin/DiT
Official PyTorch Implementation of "Scalable Diffusion Models with Transformers"
hwpengTristin/DRSA-Exo2Ego-VideoSynthesis
For cue-free E2VG problem, we propose a cue-free video-based approach termed hierarchical Dynamic memory Refinement and Semantic Alignment (DRSA). Moreover, we create a new DSO ExoEgo dataset with dynamic exocentric scenes and rich interacting objects to advance the E2VG research.
hwpengTristin/easy_handeye2
Automated, hardware-independent Hand-Eye Calibration for ROS2
hwpengTristin/fast-DiT
Fast Diffusion Models with Transformers
hwpengTristin/FastSAM
Fast Segment Anything
hwpengTristin/GA-DDPG
6D Grasping Policy from Point Clouds
hwpengTristin/handover-sim
A simulation environment and benchmark for human-to-robot object handovers
hwpengTristin/handover-sim2real
Official code for CVPR'23 paper: Learning Human-to-Robot Handovers from Point Clouds
hwpengTristin/imitation
Clean PyTorch implementations of imitation and reward learning algorithms
hwpengTristin/IRRA
Cross-Modal Implicit Relation Reasoning and Aligning for Text-to-Image Person Retrieval (CVPR 2023)
hwpengTristin/LGGAN
[CVPR 2020] Local Class-Specific and Global Image-Level Generative Adversarial Networks for Semantic-Guided Scene Generation
hwpengTristin/OpenDiT
OpenDiT: An Easy, Fast and Memory-Efficient System for DiT Training and Inference
hwpengTristin/pytorch-CycleGAN-and-pix2pix
Image-to-Image Translation in PyTorch
hwpengTristin/pytorch-image-models
PyTorch image models, scripts, pretrained weights -- ResNet, ResNeXT, EfficientNet, EfficientNetV2, NFNet, Vision Transformer, MixNet, MobileNet-V3/V2, RegNet, DPN, CSPNet, and more
hwpengTristin/realsense-ros
ROS Wrapper for Intel(R) RealSense(TM) Cameras
hwpengTristin/remp
Rearrangement with Multiple Manipulation Primitives
hwpengTristin/Sat2StrPanoramaSynthesis
Geometry-Guided Street-View Panorama Synthesis from Satellite Imagery, TPAMI 2022
hwpengTristin/segment-anything-video
MetaSeg: Packaged version of the Segment Anything repository
hwpengTristin/Ubuntu_16.04_Cuda_Cudnn
Ubuntu_16.04_Cuda_Cudnn setup
hwpengTristin/Universal_Robots_ROS2_Driver
Universal Robots ROS2 driver supporting CB3 and e-Series
hwpengTristin/Universal_Robots_ROS_Driver
Universal Robots ROS driver supporting CB3 and e-Series
hwpengTristin/ur3
ROS-based UR3/UR3e controller with simulation in Gazebo. Adaptable to other UR robots
hwpengTristin/ur5e_joystick_control
hwpengTristin/VideoCrafter
VideoCrafter2: Overcoming Data Limitations for High-Quality Video Diffusion Models