Image Tokenizers Should Be Trained Between Images
cs.CV
Submitted: 2026-10-12
Updated: 2026-10-14
Comments: Project page: https://graphics.cs.uni-tuebingen.de/papers/interptok/
Code: https://github.com/cgtuebingen/InterpTok
Project page: https://graphics.cs.uni-tuebingen.de/papers/interptok
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Sources
- Understanding Hallucinations in Diffusion Models through Mode Interpolation
- Latent Space Oddity: on the Curvature of Deep Generative Models
- On Adversarial Mixup Resynthesis
- Understanding and Improving Interpolation in Autoencoders via an Adversarial Regularizer
- Dynamical Regimes of Diffusion Models
- Emerging Properties in Self-Supervised Vision Transformers
- Masked Autoencoders Are Effective Tokenizers for Diffusion Models
- SoftVQ-VAE: Efficient 1-Dimensional Continuous Tokenizer
- Diffusion Models Beat GANs on Image Synthesis
- Taming Transformers for High-Resolution Image Synthesis
- The Prism Hypothesis: Harmonizing Semantic and Pixel Representations via Unified Autoencoding
- Smooth Diffusion: Crafting Smooth Latent Spaces in Diffusion Models
- Masked Autoencoders Are Scalable Vision Learners
- AID: Attention Interpolation of Text-to-Image Diffusion
- GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium
- Classifier-Free Diffusion Guidance
- Denoising Diffusion Probabilistic Models
- Rethinking FID: Towards a Better Evaluation Metric for Image Generation
- The relativistic discriminator: a key element missing from standard GAN
- A Style-Based Generator Architecture for Generative Adversarial Networks
Related papers
- Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
- AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
- Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
- MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
- TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
- A Survey on Efficient Vision-Language-Action Models