A curated list of resources focused on Visual AutoRegressive Modeling, makes GPT-style AR models surpass diffusion transformers in image generation.

Official PyTorch implementation of D^2-World as the second place and innovation award of CVPR 2024 Predictive World Model Challenge.

[CVPR 2023] Official implementation of the paper "Semi-DETR: Semi-Supervised Object Detection with Detection Transformers"

[CVPR 2024] Visual Point Cloud Forecasting

[ICLR24] Official implementation of the paper “MagicDrive: Street View Generation with Diverse 3D Geometry Control”

A comprehensive survey of forging vision foundation models for autonomous driving, including challenges, methodologies, and opportunities.

[ICRA 2024] RenderOcc: Vision-Centric 3D Occupancy Prediction with 2D Rendering Supervision. (Early version: UniOcc)

Collect papers and codes about VQGAN in various Computer Vision tasks