Official repo for paper "Tora: Trajectory-oriented Diffusion Transformer for Video Generation"

Multimodal Models in Real World

OmniTokenizer: one model and one weight for image-video joint tokenization.

Autoregressive Model Beats Diffusion: 🦙 Llama for Scalable Image Generation

A Generalizable World Model for Autonomous Driving

DiG: Scalable and Efficient Diffusion Models with Gated Linear Attention

[GPT beats diffusion🔥] [scaling laws in visual generation📈] Official impl. of "Visual Autoregressive Modeling: Scalable Image Generation via Next-Scale Prediction". An *ultra-simple, user-friendly …

[ICML 2024] Vision Mamba: Efficient Visual Representation Learning with Bidirectional State Space Model

[CVPR 2024] LMDrive: Closed-Loop End-to-End Driving with Large Language Models

A method that can match the 3D point cloud sub-map generated by the robot during the SLAM process with the 2D map.

[CVPR2024] Official Repository of Paper "Panacea: Panoramic and Controllable Video Generation for Autonomous Driving"

[ICRA'2024] Rethinking Imitation-based Planner for Autonomous Driving

[CVPR 2024] 4D Gaussian Splatting for Real-Time Dynamic Scene Rendering

GaussianDreamer: Fast Generation from Text to 3D Gaussians by Bridging 2D and 3D Diffusion Models (CVPR 2024)

Layout-Guided multi-view driving scene video generation with latent diffusion model

Code and documents of LongLoRA and LongAlpaca (ICLR 2024 Oral)

Official codebase for I-JEPA, the Image-based Joint-Embedding Predictive Architecture. First outlined in the CVPR paper, "Self-supervised learning from images with a joint-embedding predictive arch…

[IEEE T-PAMI] All you need for End-to-end Autonomous Driving

[CoRL'23] Parting with Misconceptions about Learning-based Vehicle Motion Planning

PyTorch code for the paper "Model-Based Imitation Learning for Urban Driving".

A curated list of awesome End-to-End Autonomous Driving resources (continually updated)

[Information Fusion (Vol.103, Mar. '24)] Boosting Image Matting with Pretrained Plain Vision Transformers

[ICCV2023] VLPart: Going Denser with Open-Vocabulary Part Segmentation

Multi-Modal 3D Object Detection by Box Matching

[CVPR 2023] Pytorch implementation of ThinkTwice, a SOTA Decoder for End-to-end Autonomous Driving under BEV.

Track-Anything is a flexible and interactive tool for video object tracking and segmentation, based on Segment Anything, XMem, and E2FGVI.