Squeeze3D: Extreme Neural Compression with Latent Space Bridging
squeeze3d.github.io
How can we bridge the latent spaces of different models? We do so without any reconstruction-based losses, only latent space loss + dimension-wise contrastive loss.
关键词：Squeeze3D, 3D compression, latent space bridging, neural compression, meshes, point clouds, radiance fields, generative models