0YJ
Follow
Starred repositories
🚀🚀 「大模型」2小时完全从0训练26M的小参数GPT！🌏 Train a 26M-parameter GPT from scratch in just 2h!
利用AI大模型，一键生成高清短视频 Generate short videos with one click using AI LLM.
[ICCV 2021] A dataset of non-rigidly deforming objects.
[CVPR 2022, Oral] Learning Partial point cloud matching in Rigid and Deformable scenes
[NeurIPS 2022] Non-rigid Point Cloud Registration with Neural Deformation Pyramid
Bayesian Coherent Point Drift / Domain Elastic Transform
[ECCV 2024]"FSGS: Real-Time Few-Shot View Synthesis using Gaussian Splatting", Zehao Zhu*, Zhiwen Fan*, Yifan Jiang, Zhangyang Wang
High-Fidelity Lip-Syncing with Wav2Lip and Real-ESRGAN
ID-Pose: Sparse-view Camera Pose Estimation by Inverting Diffusion Models
Differentiable gaussian rasterization with depth, alpha, normal map and extra per-Gaussian attributes, also support camera pose gradient
[ICCV 2023] SparseNeRF: Distilling Depth Ranking for Few-shot Novel View Synthesis
[CAAI AIR'24] Bilateral Reference for High-Resolution Dichotomous Image Segmentation
[ECCV 2024] Single Image to 3D Textured Mesh in 10 seconds with Convolutional Reconstruction Model.
Real-time face swap for PC streaming or video calls
SF3D: Stable Fast 3D Mesh Reconstruction with UV-unwrapping and Illumination Disentanglement
SPAR3D: Stable Point-Aware Reconstruction of 3D Objects from Single Images
User-friendly AI Interface (Supports Ollama, OpenAI API, ...)
Easy NeRF synthetic dataset creation within Blender
Detectron2 is a platform for object detection, segmentation and other visual recognition tasks.
DeepSeek Coder: Let the Code Write Itself
Official repo for Adaptive Rectangular Convolution
