Wanggcong

LLaMA-Factory

Unify Efficient Fine-Tuning of 100+ LLMs

deeplearning_ai_books

deeplearning.ai（吴恩达老师的深度学习课程笔记及资源）

AnimateAnyone

Animate Anyone: Consistent and Controllable Image-to-Video Synthesis for Character Animation

trl

Train transformer language models with reinforcement learning.

Dynamic3DGaussians

Awesome-Video-Diffusion-Models

[Arxiv] A Survey on Video Diffusion Models

SEINE

[ICLR 2024] SEINE: Short-to-Long Video Diffusion Model for Generative Transition and Prediction

materials_discovery

Deformable-3D-Gaussians

[CVPR 2024] Official implementation of "Deformable 3D Gaussians for High-Fidelity Monocular Dynamic Scene Reconstruction"

splatter-image

Official implementation of `Splatter Image: Ultra-Fast Single-View 3D Reconstruction' CVPR 2024

EdgeSAM

Official PyTorch implementation of "EdgeSAM: Prompt-In-the-Loop Distillation for On-Device Deployment of SAM"

street_gaussians

Code for "Street Gaussians for Modeling Dynamic Urban Scenes"

TRIPS

dreamgaussian4d

[arXiv 2023] DreamGaussian4D: Generative 4D Gaussian Splatting

LLaMA-Pro

[ACL 2024] Progressive LLaMA with Block Expansion.

GauHuman

Code for our CVPR'2024 paper "GauHuman: Articulated Gaussian Splatting from Monocular Human Videos"

3d-cinemagraphy

[CVPR 2023] 3D Cinemagraphy from a Single Image

PrimDiffusion

[NeurIPS 2023] PrimDiffusion: Volumetric Primitives Diffusion for 3D Human Generation

DISCNet

Code for DISCNet.

w-plus-adapter

[CVPR 2024] When StyleGAN Meets Stable Diffusion: a W+ Adapter for Personalized Image Generation

OpenPVSG

Benchmarking Panoptic Video Scene Graph Generation (PVSG), CVPR'23

Stylizing-3D-Scene

AlignFormer

Official implementation of "Generating Aligned Pseudo-Supervision from Non-Aligned Data for Image Restoration in Under-Display Camera"

DPI

Robust-MonoDepth

A new baseline and benchmark for robust monocular depth estimation

neusky

The Sky's the Limit: Relightable Outdoor Scenes via a Sky-pixel Constrained Illumination Prior and Outside-In Visibility

DNE4Hand

Grounded-Segment-Anything

Grounded-SAM: Marrying Grounding-DINO with Segment Anything & Stable Diffusion & Recognize Anything - Automatically Detect , Segment and Generate Anything

4D-Humans

4DHumans: Reconstructing and Tracking Humans with Transformers

materials_discovery