zju3dv

让人体动作捕捉更简单

论文“LoFTR: Detector-Free Local Feature Matching with Transformers”代码 (CVPR 2021, T-PAMI 2022)

“GVHMR: World-Grounded Human Motion Recovery via Gravity-View Coordinates”代码，Siggraph Asia 2024, TPAMI 2026

[CVPR 2024] 4K4D：4K 分辨率下的实时 4D 视角合成。

[SIGGRAPH Asia 2023 (Technical Communications)] EasyVolcap：加速神经体积视频研究

[ECCV 2024] Street Gaussians: 使用 Gaussian Splatting 对动态城市场景进行建模

“MatchAnything: Universal Cross-Modality Image Matching with Large-Scale Pre-Training”论文代码，TPAMI 2026。

CVPR 2020 oral 论文「Deep Snake for Real-Time Instance Segmentation」的代码

[TVCG2024] PGSR：基于平面的高斯分布 splatting，用于高效且高保真的曲面重建

[CVPR 2026] InfiniDepth：基于神经隐式场的任意分辨率与细粒度深度估计

CVPR 2024 论文“Efficient LoFTR: Semi-Dense Local Feature Matching with Sparse-Like Speed”的代码

「OnePose: One-Shot Object Pose Estimation without CAD Models」(CVPR 2022) 论文代码

“Neural Body: Implicit Neural Representations with Structured Latent Codes for Novel View Synthesis of Dynamic Humans” CVPR 2021 最佳论文候选代码

"PVNet: Pixel-wise Voting Network for 6DoF Pose Estimation" CVPR 2019 oral 论文代码

Gaussians 的层级

“Detector-Free Structure from Motion”的代码，CVPR 2024

[ICCV 2025] Diffuman4D：基于时空扩散模型的稀疏视角视频 4D 一致性人物视角合成

[CVPR 2026 (Highlight)] Scal3R：用于大规模 3D 重建的可扩展测试时训练。

TPAMI 2024 与 ICCV 2021 论文“Animatable Implicit Neural Representations for Creating Realistic Avatars from Videos”的代码