Tag
Sperid Labs 发布 Idol,能将单张物体照片在 2 秒内转换为包含被遮挡面的 3D Gaussian splat(最多约 100 万个高斯),可在消费级 GPU 上以 7.2GB 显存运行。
提出RAESR,利用冻结DINOv3-L的23层融合层作为超分辨率的潜空间基底,训练415M解码器将退化嵌入映射回流形,在RealSR、DRealSR、LSDIR和DIV2K-Val上实现最优的保真度-感知权衡,且单张H20 GPU上每512×512图像仅需37ms。
This post explores DINOv3 vision embeddings by generating images that correspond to specific embedding directions, using gradient optimization and augmentation strategies to invert the model.
Meta Superintelligence Labs released SAM 3D Body (3DB), a promptable model for single-image full-body 3D human mesh recovery that achieves state-of-the-art performance in the wild, built on the new Momentum Human Rig parametric mesh representation and supporting auxiliary prompts like 2D keypoints and masks.