ZJU3DV
ZJU3DV is a research group of State Key Lab of CAD&CG, Zhejiang University. We focus on the research of 3D computer vision, SLAM and AR.
Hangzhou, China
Pinned Repositories
4K4D
[CVPR 2024] 4K4D: Real-Time 4D View Synthesis at 4K Resolution
EasyMocap
Make human motion capture easier.
EasyVolcap
[SIGGRAPH Asia 2023 (Technical Communications)] EasyVolcap: Accelerating Neural Volumetric Video Research
LoFTR
Code for "LoFTR: Detector-Free Local Feature Matching with Transformers", CVPR 2021, T-PAMI 2022
neuralbody
Code for "Neural Body: Implicit Neural Representations with Structured Latent Codes for Novel View Synthesis of Dynamic Humans" CVPR 2021 best paper candidate
NeuralRecon
Code for "NeuralRecon: Real-Time Coherent 3D Reconstruction from Monocular Video", CVPR 2021 oral
OnePose
Code for "OnePose: One-Shot Object Pose Estimation without CAD Models", CVPR 2022
pvnet
Code for "PVNet: Pixel-wise Voting Network for 6DoF Pose Estimation" CVPR 2019 oral
snake
Code for "Deep Snake for Real-Time Instance Segmentation" CVPR 2020 oral
street_gaussians
[ECCV 2024] Street Gaussians: Modeling Dynamic Urban Scenes with Gaussian Splatting
ZJU3DV's Repositories
zju3dv/4K4D
[CVPR 2024] 4K4D: Real-Time 4D View Synthesis at 4K Resolution
zju3dv/EasyVolcap
[SIGGRAPH Asia 2023 (Technical Communications)] EasyVolcap: Accelerating Neural Volumetric Video Research
zju3dv/OnePose
Code for "OnePose: One-Shot Object Pose Estimation without CAD Models", CVPR 2022
zju3dv/street_gaussians
[ECCV 2024] Street Gaussians: Modeling Dynamic Urban Scenes with Gaussian Splatting
zju3dv/pvnet
Code for "PVNet: Pixel-wise Voting Network for 6DoF Pose Estimation" CVPR 2019 oral
zju3dv/LoG
Level of Gaussians
zju3dv/EfficientLoFTR
Code for "Efficient LoFTR: Semi-Dense Local Feature Matching with Sparse-Like Speed", CVPR 2024
zju3dv/DetectorFreeSfM
Code for "Detector-Free Structure from Motion", CVPR 2024
zju3dv/PGSR
[TVCG2024] PGSR: Planar-based Gaussian Splatting for Efficient and High-Fidelity Surface Reconstruction
zju3dv/GVHMR
Code for "GVHMR: World-Grounded Human Motion Recovery via Gravity-View Coordinates", Siggraph Asia 2024
zju3dv/NeuMesh
Code for "MeuMesh: Learning Disentangled Neural Mesh-based Implicit Field for Geometry and Texture Editing", ECCV 2022 Oral
zju3dv/IntrinsicAnything
zju3dv/GeneAvatar
Code for "GeneAvatar: Generic Expression-Aware Volumetric Head Avatar Editing from a Single Image", CVPR 2024
zju3dv/SAM-Graph
Code for "SAM-guided Graph Cut for 3D Instance Segmentation" ECCV 2024
zju3dv/zju3dv.github.io
zju3dv/text_scene_motion
[CVPR 2024] Generating Human Motion in 3D Scenes from Text Descriptions
zju3dv/street_crafter
StreetCrafter: Street View Synthesis with Controllable Video Diffusion Models
zju3dv/Motion-2-to-3
Code for "Motion-2-to-3: Leveraging 2D Motion Data to Boost 3D Motion Generation", Arxiv 2024
zju3dv/hghoi
ICCV 2023, Hierarchical Generation of Human-Object Interactions with Diffusion Probabilistic Models
zju3dv/NIID-Net
Code for "NIID-Net: Adapting Surface Normal Knowledge for Intrinsic Image Decomposition in Indoor Scenes" TVCG
zju3dv/DATAP-SfM
DATAP-SfM: Dynamic-Aware Tracking Any Point for Robust Dense Structure from Motion in the Wild
zju3dv/MagLoc-AR
zju3dv/DiffPano
[NeurIPS2024] DiffPano: Scalable and Consistent Text to Panorama Generation with Spherical Epipolar-Aware Diffusion
zju3dv/ND-SDF
ND-SDF: Learning Normal Deflection Fields for High-Fidelity Indoor Reconstruction
zju3dv/100-Phones
zju3dv/MVN-AFM
Code for "Multi-View Neural 3D Reconstruction of Micro-/Nanostructures with Atomic Force Microscopy"
zju3dv/FedSurfGS
FedSurfGS: Scalable 3D Surface Gaussian Splatting with Federated Learning for Large Scene Reconstruction
zju3dv/RNNPose
RNNPose: Recurrent 6-DoF Object Pose Refinement with Robust Correspondence Field Estimation and Pose Optimization, CVPR 2022
zju3dv/BBCNet
zju3dv/PanoIndoor