This repository aggregates papers from the CVPR 2024 conference along with their official code implementations and demo videos. It covers topics spanning object detection, semantic segmentation, diffusion models, text-to-image generation, multimodal learning, and neural rendering (NeRF). The project maintains archives for CVPR 2021–2023 and links to other top conferences like ICCV and ECCV, serving as a comprehensive reference for the computer vision research community.