几篇论文实现代码：
《PRM: Photometric Stereo based Large Reconstruction Model》(2024) GitHub: github.com/g3956/PRM [fig1]
《D3RoMa: Disparity Diffusion-based Depth Sensing for Material-Agnostic Robotic Manipulation》(2024) GitHub: github.com/songlin/d3roma
《Towards Interpreting Visual Information Processing in Vision-Language Models》(2024) GitHub: github.com/clemneo/llava-interp
《EasyHOI: Unleashing the Power of Large Models for Reconstructing Hand-Object Interactions in the Wild》(2024) GitHub: github.com/lym29/EasyHOI
《LatentSync: Audio Conditioned Latent Diffusion Models for Lip Sync》(2024) GitHub: github.com/bytedance/LatentSync [fig2]
《YOLO-UniOW: Efficient Universal Open-World Object Detection》(2024) GitHub: github.com/THU-MIG/YOLO-UniOW [fig3]
#人工智能##AI创造营#
《PRM: Photometric Stereo based Large Reconstruction Model》(2024) GitHub: github.com/g3956/PRM [fig1]
《D3RoMa: Disparity Diffusion-based Depth Sensing for Material-Agnostic Robotic Manipulation》(2024) GitHub: github.com/songlin/d3roma
《Towards Interpreting Visual Information Processing in Vision-Language Models》(2024) GitHub: github.com/clemneo/llava-interp
《EasyHOI: Unleashing the Power of Large Models for Reconstructing Hand-Object Interactions in the Wild》(2024) GitHub: github.com/lym29/EasyHOI
《LatentSync: Audio Conditioned Latent Diffusion Models for Lip Sync》(2024) GitHub: github.com/bytedance/LatentSync [fig2]
《YOLO-UniOW: Efficient Universal Open-World Object Detection》(2024) GitHub: github.com/THU-MIG/YOLO-UniOW [fig3]
#人工智能##AI创造营#
