Stars
A PyTorch implementation of the paper "EDGS: Eliminating Densification for Efficient Convergence of 3DGS"
[NeurIPS'2024]: DiffGS: Functional Gaussian Splatting Diffusion
[CVPR 2025] UniScene: Unified Occupancy-centric Driving Scene Generation
Speedup the attention computation of Swin Transformer
Cosmos-Transfer1 is a world-to-world transfer model designed to bridge the perceptual divide between simulated and real-world environments.
[CVPR 2025 Oral] VGGT: Visual Geometry Grounded Transformer
Connected components on discrete and continuous multilabel 3D & 2D images. Handles 26, 18, and 6 connected variants; periodic boundaries (4, 8, & 6)
Builder and index for PyTorch packages
[CVPR 2024 Highlight] GenAD: Generalized Predictive Model for Autonomous Driving & Foundation Models in Autonomous System
[ICLR 2025 Spotlight] Official implementation for "DynamicCity: Large-Scale 4D Occupancy Generation from Dynamic Scenes"
Official implementation of Continuous 3D Perception Model with Persistent State
Schedule-Free Optimization in PyTorch
🔥Highlighting the top ML papers every week.
[NeurIPS 2024 Best Paper][GPT beats diffusion🔥] [scaling laws in visual generation📈] Official impl. of "Visual Autoregressive Modeling: Scalable Image Generation via Next-Scale Prediction". An *ult…
[ECCV 2024 Oral] LGM: Large Multi-View Gaussian Model for High-Resolution 3D Content Creation.
This project aim to reproduce Sora (Open AI T2V model), we wish the open source community contribute to this project.
Annotated version of the Mamba paper
3D Occupancy Prediction Benchmark in Autonomous Driving
[CVPR 2024 Highlight] Feature 3DGS: Supercharging 3D Gaussian Splatting to Enable Distilled Feature Fields
[CVPR 2024] Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data. Foundation Model for Monocular Depth Estimation
Awesome-LLM-3D: a curated list of Multi-modal Large Language Model in 3D world Resources
[ICML 2024] Vision Mamba: Efficient Visual Representation Learning with Bidirectional State Space Model