SEAL changes 5% of face pixels to block diffusion identity cloning
On CelebA-HQ and VGGFace2, protected images stay above 41 dB PSNR while identity similarity falls to at most 0.15.
Stories per day · 30 days
2 RSS
Relatedadversarial-perturbation1deformable-bodies1diffusion1diffusion-models1face-privacy1flow-matching1generative-models1identity-protection1image-generation1image-restoration1latent-diffusion1latent-models1low-light-enhancement1neural-simulation1physics-simulation1visual-tokenizer1
10 stories, newest first · one card per story
Stories tagged #vae
GLOW-FM enhances low-light images with one latent flow step
The small variant uses a frozen Tiny-VAE and Terminal Velocity Matching at 34 GFLOPs and one function evaluation.
RoAR-VAE improves latent diffusability via robust prediction
It beats the strongest baseline tokenizer by 2.19 points and FLUX.1-VAE small-text accuracy by 16.93 points.
PhysLDM applies latent diffusion to deformable mesh simulation
A spatiotemporal VAE reports about 2.48 mm reconstruction error at up to 78x token compression.
Partially Observable Zero-shot coordination by Predicting Intention of Partner
PIP improves zero-shot multi-agent coordination when partners are intermittently out of view.
Empirical Variational Autoencoder
Empirical VAE learns autoregressive latent priors with one linear layer, matching diffusion quality at faster inference.
SILSA: Sliding-Window Slice Latents for Topology-Preserving High-Resolution 3D Generation
SILSA generates high-resolution 3D shapes from sliding-window slice latents, using far fewer tokens and improving topology.
SILSA: Sliding-Window Slice Latents for Topology-Preserving High-Resolution 3D Generation
SILSA generates high-resolution 3D shapes from compact slice latents while preserving topology and cutting token cost.
Does Native 3D Texture Generation Necessarily Require 3D Assets for Training?
Tex-Zero trains native 3D texture models from constructed 2D image planes, without real 3D assets.
TransNormal-2: Geometry-Grounded Rectified Flow with Edge-Aware Decoding for Precise Normal Estimation
TransNormal-2 improves monocular surface-normal estimation by fixing VAE edge degradation with geometry-aware losses and refinement, matching MoGe-2 with 1.4% of annotations.