paper-with-me

Papers

Latent Diffusion Model without Variational Autoencoder

2025-10-17 · Minglei Shi, Haolin Wang, Wenzhao Zheng, Ziyang Yuan, Xiaoshi Wu, Xintao Wang, Pengfei Wan, Jie Zhou, Jiwen Lu arxiv

Recent progress in diffusion-based visual generation has largely relied on latent diffusion models with variational autoencoders (VAEs). While effective for high-fidelity synthesis, this VAE+diffusion paradigm suffers from limited training efficiency, slow inference, and poor transferability to broader vision tasks. These issues stem from a key limitation of VAE latent spaces: the lack of clear semantic separation and strong discriminative structure. Our analysis confirms that these properties are crucial not only for perception and understanding tasks, but also for the stable and efficient training of latent diffusion models. Motivated by this insight, we introduce SVG, a novel latent diffusion model without variational autoencoders, which leverages self-supervised representations for visual generation. SVG constructs a feature space with clear semantic discriminability by leveraging frozen DINO features, while a lightweight residual branch captures fine-grained details for high-fidelity reconstruction. Diffusion models are trained directly on this semantically structured latent space to facilitate more efficient learning. As a result, SVG enables accelerated diffusion training, supports few-step sampling, and improves generative quality. Experimental results further show that SVG preserves the semantic and discriminative capabilities of the underlying self-supervised representations, providing a principled pathway toward task-general, high-quality visual representations. Code and interpretations are available at https://howlin-wang.github.io/svg/.

📄 PDF Abstract BibTeX arXiv:2510.15301

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Diffusion Variational Autoencoders

2019-01-25 · Luis A. Pérez Rey, Vlado Menkovski, Jacobus W. Portegies

A standard Variational Autoencoder, with a Euclidean latent space, is structurally incapable of capturing topological properties of certain datasets. To remove topological obstructions, we introduce Diffusion Variational…

Latent Diffusion Models with Masked AutoEncoders

2025-07-14 · Junho Lee, Jeongwoo Shin, Hyungwook Choi, Joonseok Lee arxiv

In spite of the remarkable potential of Latent Diffusion Models (LDMs) in image generation, the desired properties and optimal design of the autoencoders have been underexplored. In this work, we analyze the role of auto…

Image Generation

Latent-Compressed Variational Autoencoder for Video Diffusion Models

2026-04-12 · Jiarui Guan, Wenshuai Zhao, Zhengtao Zou, Juho Kannala 외 arxiv

Video variational autoencoders (VAEs) used in latent diffusion models typically require a sufficiently large number of latent channels to ensure high-quality video reconstruction. However, recent studies have revealed th…

Video Reconstruction

Text-to-speech synthesis based on latent variable conversion using diffusion probabilistic model and variational autoencoder

2022-12-16 · Yusuke Yasuda, Tomoki Toda

Text-to-speech synthesis (TTS) is a task to convert texts into speech. Two of the factors that have been driving TTS are the advancements of probabilistic models and latent representation learning. We propose a TTS metho…

Representation LearningSpeech Synthesistext-to-speechText to Speech+1

CoVAE: Consistency Training of Variational Autoencoders

2025-07-12 · Gianluigi Silvestri, Luca Ambrogioni arxiv

Current state-of-the-art generative approaches frequently rely on a two-stage training procedure, where an autoencoder (often a VAE) first performs dimensionality reduction, followed by training a generative model on the…

Dimensionality Reduction