[CVPR 2025] "DiC: Rethinking Conv3x3 Designs in Diffusion Models", a performant & speedy Conv3x3 diffusion model.

[NeurIPS 2024] "DreamMesh4D: Video-to-4D Generation with Sparse-Controlled Gaussian-Mesh Hybrid Representation"

Code repository for Zero123++: a Single Image to Consistent Multi-view Diffusion Base Model.

3DILG: Irregular Latent Grids for 3D Generative Modeling

[ICCV 2025] From anything to mesh like human artists. Official impl. of "MeshAnything V2: Artist-Created Mesh Generation With Adjacent Mesh Tokenization"

Open-source framework for building human-intervenable deep research agents with real-time collaboration between humans and AI. Features multi-agent architecture, comprehensive tool suite, and web-b…

Now, Stronger AI Pushes Frontiers, Stronger Our Shared Future.

[TNNLS 24] Beyond Photometric Consistency: Geometry-based Occlusion-aware Unsupervised Light Field Disparity Estimation

This is the official implementation of GNF (Gaussian Neural Fields)

TriplaneGaussian: A new hybrid representation for single-view 3D reconstruction.

ReconViaGen: Towards Accurate Multi-view 3D Object Reconstruction via Generation

Official implementation of the paper "Exploring Non-Local Spatial-Angular Correlations with a Hybrid Mamba-Transformer Framework for Light Field Super-Resolution"

AutoGPT is the vision of accessible AI for everyone, to use and to build on. Our mission is to provide the tools, so that you can focus on what matters.

[TVCG2024] PGSR: Planar-based Gaussian Splatting for Efficient and High-Fidelity Surface Reconstruction

[NeurIPS'24] NeuRodin: A Two-stage Framework for High-Fidelity Neural Surface Reconstruction

Code of π^3: Permutation-Equivariant Visual Geometry Learning

Decoupling and Aggregating: Dual-layer Light Field Depth Estimation with Reflective and Transparent Surfaces

"DeepCode: Open Agentic Coding (Paper2Code & Text2Web & Text2Backend)"

Paper2Code: Automating Code Generation from Scientific Papers in Machine Learning

[TMM'2025] RCNet: Deep Recurrent Collaborative Network for Multi-View Low-Light Image Enhancement

基于Python的开源量化交易平台开发框架

The official repository for ERNIE 4.5 and ERNIEKit – its industrial-grade development toolkit based on PaddlePaddle.

Wan: Open and Advanced Large-Scale Video Generative Models

Multi-Stream Progressive Restoration for Low-Light Light Field Enhancement and Denoising

Official PyTorch implementation of the paper "Dataset Distillation with Neural Characteristic Function: A Minmax Perspective" (NCFM) in CVPR 2025 (Highlight).

The repository for CVPR 2022 Paper "Neural 3D Video Synthesis"

Academic Survey Paper Generation.