Yi-Hsuan Tsai

Exemplar_Masking_MCIL. Exemplar Masking for Multimodal Incremental Learning

RankingAwareCLIP. [ICLR'25] Official repository of paper: Ranking-aware adapter for text-driven image ordering with CLIP

VCD_Analysis. Delve into Visual Contrastive Decoding for Hallucination Mitigation of Large Vision-Language Models

DiffPoseTalk. DiffPoseTalk: Speech-Driven Stylistic 3D Facial Animation and Head Pose Generation via Diffusion Models

TalkingGaussian. [ECCV'24] TalkingGaussian: Structure-Persistent 3D Talking Head Synthesis via Gaussian Splatting

ray_casting_mlc. [ECCV'24] Self-training Room Layout Estimation via Geometry-aware Ray-casting

CE3D. Official Implementation of ECCV2024 paper: Chat Edit 3D: Interactive 3D Scene Editing via Large Language Model

hallo. Hallo: Hierarchical Audio-Driven Visual Synthesis for Portrait Image Animation

DiffTalk. [CVPR2023] The implementation for "DiffTalk: Crafting Diffusion Models for Generalized Audio-Driven Portraits Animation"

GaussianTalker. Official implementation of “GaussianTalker: Real-Time High-Fidelity Talking Head Synthesis with Audio-Driven 3D Gaussian Splatting” by Kyusun Cho, Joungbin Lee, Heeji Yoon, Yeobin Hong, Jaehoon Ko, Sangjun Ahn and Seungryong Kim

360-mlc. [NeurIPS'22] 360-MLC: Multi-view Layout Consistency for Self-training and Hyper-parameter Tuning

Gaga. [TMLR 2026] Gaga: Group Any Gaussians via 3D-aware Memory Bank

Action-slot. [CVPR 2024] Action-slot: Visual Action-centric Representations for Atomic Activity Recognition in Traffic Scenes

Learnable_Regions. [CVPR 2024] Official code for "Text-Driven Image Editing via Learnable Regions"

PTT. [CVPR2024] PTT: Point-Trajectory Transformer for Efficient Temporal 3D Object Detection

VG-W3D. [ECCV2024] Weakly Supervised 3D Object Detection via Multi-Level Visual Guidance

Diffusion-SS3D. Python

awesome_talking_face_generation.

awesome-talking-head-generation.

Awesome-Talking-Face. 📖 A curated list of resources dedicated to talking face.

StyleSync. Official code of CVPR '23 paper "StyleSync: High-Fidelity Generalized and Personalized Lip Sync in Style-based Generator"

MoMA-M3T. Delving into Motion-Aware Matching for Monocular 3D Object Tracking (ICCV 2023)

HRDA. [ECCV22] Official Implementation of HRDA: Context-Aware High-Resolution Domain-Adaptive Semantic Segmentation

omni3d. Code release for "Omni3D A Large Benchmark and Model for 3D Object Detection in the Wild"

segment-anything. The repository provides code for running inference with the SegmentAnything Model (SAM), links for downloading the trained model checkpoints, and example notebooks that show how to use the model.

mvl_toolkit. Official toolkit for Multi-View Layout Estimation Challenge in OmniCV workshop at CVPR'23.

missing_aware_prompts. Multimodal Prompting with Missing Modalities for Visual Recognition, CVPR'23

VPD. [ICCV 2023] VPD is a framework that leverages the high-level and low-level knowledge of a pre-trained text-to-image diffusion model to downstream visual perception tasks.

CMKD. Cross-Modality Knowledge Distillation Network for Monocular 3D Object Detection (ECCV 2022 Oral)

OPA. Python

weak-da-seg. Unsupervised domain adaptation of semantic segmentation models using weak labels

Ultra-Fast-Lane-Detection-v2. Ultra Fast Deep Lane Detection With Hybrid Anchor Driven Ordinal Classification (TPAMI 2022)

BiFusev2. BiFuse++: Self-supervised and Efficient Bi-projection Fusion for 360 Depth Estimation

3D-PL. [ECCV2022] 3D-PL: Domain Adaptive Depth Estimation with 3D-aware Pseudo-Labeling

direct_360_FPE. [RA-L'22] 360-DFPE: Leveraging Monocular 360-Layouts for Direct Floor Plan Estimation

monodle. Delving into Localization Errors for Monocular 3D Object Detection, CVPR'2021

conditional-lane-detection. Python

DRFT. End-to-end Multi-modal Video Temporal Grounding, NeurIPS 2021

TopFormer. TopFormer: Token Pyramid Transformer for Mobile Semantic Segmentation, CVPR2022

Cream. This is a collection of our NAS and Vision Transformer work.

OpenLane. [ECCV 2022 Oral] OpenLane: Large-scale Realistic 3D Lane Dataset

pytorch-auto-drive. PytorchAutoDrive: Segmentation models (ERFNet, ENet, DeepLab, FCN...) and Lane detection models (SCNN, RESA, LSTR, LaneATT, BézierLaneNet...) based on PyTorch with fast training, visualization, benchmarking & deployment help

ssdg-benchmark. Benchmarks for semi-supervised domain generalization.

lang-seg. Language-Driven Semantic Segmentation

DAFormer. [CVPR22] Official Implementation of DAFormer: Improving Network Architectures and Training Strategies for Domain-Adaptive Semantic Segmentation

openpilot. openpilot is an operating system for robotics. Currently, it upgrades the driver assistance system on 300+ supported cars.

Ultra-Fast-Lane-Detection. Ultra Fast Structure-aware Deep Lane Detection (ECCV 2020)

InterpretableMDE. Code repo for "Towards Interpretable Deep Networks for Monocular Depth Estimation" paper.

pytorch-lightning. Pretrain, finetune ANY AI model of ANY size on 1 or 10,000+ GPUs with zero code changes.

HRNet-MaskRCNN-Benchmark. Object detection with multi-level representations generated from deep high-resolution representation learning (HRNetV2h).

robust_360_8PA. [ICRA'20] Robust 360-8PA": Redesigning The Normalized 8-point Algorithm for 360-FoV Images

cvat. Computer Vision Annotation Tool (CVAT) is a leading platform for building high-quality visual datasets for vision AI. It offers open-source, cloud, and enterprise products, as well as labeling services, for image, video, and 3D annotation with AI-assisted labeling, quality assurance, team collaboration, analytics, and developer APIs.

splitnet. Code for SplitNet paper

RefContrast. Understanding Synonymous Referring Expressions via Contrastive Features

GibsonSim2RealChallenge. GibsonSim2RealChallenge @ CVPR2020

xmuda. Cross-Modal Unsupervised Domain Adaptationfor 3D Semantic Segmentation

LED2-Net. CVPR 2021 Oral paper "LED2-Net: Monocular 360˚ Layout Estimation via Differentiable Depth Rendering" official PyTorch implementation.

UniDet. Object detection on multiple datasets with an automatically learned unified label space.

PyTorch-StudioGAN. StudioGAN is a Pytorch library providing implementations of representative Generative Adversarial Networks (GANs) for conditional/unconditional image generation.

CoCLR. [NeurIPS'20] Self-supervised Co-Training for Video Representation Learning. Tengda Han, Weidi Xie, Andrew Zisserman.

SlowFast. PySlowFast: video understanding codebase from FAIR for reproducing state-of-the-art video models.

EveryPixelMatters. Implementation of ECCV 2020 paper "Every Pixel Matters: Center-aware Feature Alignment for Domain Adaptive Object Detector"

ColorizeDepthNet. PyTorch implementation for Colorization of Depth Map via Disentanglement

BiFuse. [CVPR2020] BiFuse: Monocular 360 Depth Estimation via Bi-Projection Fusion

Semantic-CariGANs. Learning to Caricature via Semantic Shape Transformation, IJCV 2021

PySyft. Perform data science on data that remains in someone else's server

Codes-for-Lane-Detection. Learning Lightweight Lane Detection CNNs by Self Attention Distillation (ICCV 2019)

detr. End-to-End Object Detection with Transformers

HRNet-Semantic-Segmentation. The OCR approach is rephrased as Segmentation Transformer: https://arxiv.org/abs/1909.11065. This is an official implementation of semantic segmentation for HRNet. https://arxiv.org/abs/1908.07919

face-parsing.PyTorch. Using modified BiSeNet for face parsing in PyTorch

mseg-api. An Official Repo of CVPR '20 "MSeg: A Composite Dataset for Multi-Domain Segmentation"

LADN. This is the implementation for Local Adversarial Disentangling Network for Facial Makeup and De-Makeup

DropGrad. Regularizing Meta-Learning via Gradient Dropout

LayoutMP3D.

SC-CAM. SC-CAM: Weakly-Supervised Semantic Segmentation via Sub-category Exploration (CVPR 2020)

Graphonomy. Graphonomy: Universal Human Parsing via Graph Transfer Learning

awesome-self-supervised-learning. A curated list of awesome self-supervised methods

awesome-point-cloud-analysis. A list of papers and datasets about point cloud analysis (processing)

detectron2. Detectron2 is a platform for object detection, segmentation and other visual recognition tasks.

360SD-Net. Pytorch implementation of ICRA 2020 paper "360° Stereo Depth Estimation with Learnable Cost Volume"

wandb. The AI developer platform. Use Weights & Biases to train and fine-tune models, and manage models from experimentation to production.

DA_detection. Progressive Domain Adaptation for Object Detection

TorchRay. Understanding Deep Networks via Extremal Perturbations and Smooth Masks

maskrcnn-benchmark. Fast, modular reference implementation of Instance Segmentation and Object Detection algorithms in PyTorch.

PointRCNN. PointRCNN: 3D Object Proposal Generation and Detection from Point Cloud, CVPR 2019.

CenterNet. Object detection, 3D detection, and pose estimation using center point detection:

CariFaceParsing. Code for ICIP2019 paper：Weakly-supervised Caricature Face Parsing through Domain Adaptation

BDL. Python

BridgeDepthFlow. Bridging Stereo Matching and Optical Flow via Spatiotemporal Correspondence, CVPR 2019

PnP-Depth. Implementation for "Plug-and-Play: Improve Depth Prediction via Sparse Data Propagation"

Stereo-LiDAR-CCVNorm. Implementation of "Stereo and LiDAR Fusion using Stereo Matching Network with Conditional Cost Volume Normalization"

second.pytorch. PointPillars for KITTI object detection

pytorch-segmentation-toolbox. PyTorch Implementations for DeeplabV3 and PSPNet

TransferSeg. Unseen Object Segmentation in Videos via Transferable Representations, ACCV 2018 (oral)

MCD_DA. Python

lang2seg. Referring Expression Object Segmentation with Caption-Aware Consistency, BMVC 2019

PyTorch-Encoding. A CV Toolkit

tensorboardX. tensorboard for pytorch (and chainer, mxnet, numpy, ...)

cycada_release. Code to accompany ICML 2018 paper

SIMS. Semi-parametric Image Synthesis

faster-rcnn.pytorch. A faster pytorch implementation of faster r-cnn

FAVOS. Demo code of the paper "Fast and Accurate Online Video Object Segmentation via Tracking Parts", in CVPR 2018

eva-stereo-matching. Python

Detectron.pytorch. A pytorch implementation of Detectron. Both training from scratch and inferring directly from pretrained Detectron weights are available.

video_seg. OSMN: One-Shot Modulation Network for Semi-supervised Video Segmentation

PyTorch-Encoding. A CV toolkit for my papers.

AdvSemiSeg. Adversarial Learning for Semi-supervised Semantic Segmentation, BMVC 2018

Detectron. FAIR's research platform for object detection research, implementing popular algorithms like Mask R-CNN and RetinaNet.

ai2thor. An open-source platform for Visual AI.

Mask_RCNN. Mask R-CNN for object detection and instance segmentation on Keras and TensorFlow

pix2pixHD. Synthesizing and manipulating 2048x1024 images with conditional GANs

Pytorch-Deeplab. DeepLab-ResNet rebuilt in Pytorch

capsule-networks. A PyTorch implementation of the NIPS 2017 paper "Dynamic Routing Between Capsules".

pytorch-semantic-segmentation. PyTorch for Semantic Segmentation

pytorch-CycleGAN-and-pix2pix. Image-to-Image Translation in PyTorch

pytorch-semseg. Semantic Segmentation Architectures Implemented in PyTorch

Seg-with-SPN. Demo code of the paper: "Learning to Segment Instances in Videos with Spatial Propagation Network", in CVPR'17 Workshop on DAVIS Challenge

GCPNet. Scene Parsing with Global Context Embedding, ICCV 2017

SegFlow. Demo code of the paper "SegFlow: Joint Learning for Video Object Segmentation and Optical Flow", in ICCV 2017

spynet. Spatial Pyramid Network for Optical Flow