dinov3

Tag

Cards List
#dinov3

speridlabs/idol

Hugging Face Models Trending ↗ · 2026-10-28 Cached

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。

0 favorites 0 likes
#dinov3

Super-Resolution in The Right Latent Space: A Frozen Vision-Foundation Substrate

Hugging Face Daily Papers ↗ · 2026-10-08 Cached

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。

0 favorites 0 likes
#dinov3

Playing with Vision Embeddings

Hacker News Top ↗ · 2026-06-05 Cached

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.

0 favorites 0 likes
#dinov3

facebook/sam-3d-body-dinov3

Hugging Face Models Trending ↗ · 2025-11-17 Cached

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.

0 favorites 0 likes
← Back to home

Submit Feedback