Related papers: Exploring the latent space of diffusion models dir…
Deep learning-based image generation has seen significant advancements with diffusion models, notably improving the quality of generated images. Despite these developments, generating images with unseen characteristics beneficial for…
High quality facial image editing is a challenging problem in the movie post-production industry, requiring a high degree of control and identity preservation. Previous works that attempt to tackle this problem may suffer from the…
World model-based policy evaluation is a practical proxy for testing real-world robot control by rolling out candidate actions in action-conditioned video diffusion models. As these models increasingly adopt latent diffusion modeling (LDM),…
The rapid advancement of pretrained text-driven diffusion models has significantly enriched applications in image generation and editing. However, as the demand for personalized content editing increases, new challenges emerge especially…
We describe a method to train a generative model with latent factors that are (approximately) independent and localized. This means that perturbing the latent variables affects only local regions of the synthesized image, corresponding to…
Selective manipulation of data attributes using deep generative models is an active area of research. In this paper, we present a novel method to structure the latent space of a Variational Auto-Encoder (VAE) to encode different…
A significant research effort is focused on exploiting the amazing capacities of pretrained diffusion models for the editing of images.They either finetune the model, or invert the image in the latent space of the pretrained model. However,…
Different encodings of datapoints in the latent space of latent-vector generative models may result in more or less effective and disentangled characterizations of the different explanatory factors of variation behind the data. Many works…
Deep neural networks achieve impressive performance but remain difficult to interpret and control. We present SALVE (Sparse Autoencoder-Latent Vector Editing), a unified "discover, validate, and control" framework that bridges mechanistic…
Linear transformation techniques such as singular value decomposition (SVD) have been used widely to gain insight into the qualitative dynamics of data generated by dynamical systems. There have been several reports in the past that had…
The latent space of diffusion model mostly still remains unexplored, despite its great success and potential in the field of generative modeling. In fact, the latent space of existing diffusion models are entangled, with a distorted mapping…
Disentangling factors of variation within data has become a very challenging problem for image generation tasks. Current frameworks for training a Generative Adversarial Network (GAN), learn to disentangle the representations of the data in…
Generative modeling of 3D shapes has become an important problem due to its relevance to many applications across Computer Vision, Graphics, and VR. In this paper we build upon recently introduced 3D mesh-convolutional Variational…
Navigating in the latent space of StyleGAN has shown effectiveness for face editing. However, the resulting methods usually encounter challenges in complicated navigation due to the entanglement among different attributes in the latent…
We present a cascaded diffusion model based on a part-level implicit 3D representation. Our model achieves state-of-the-art generation quality and also enables part-level shape editing and manipulation without any additional training in…
Singular Value Decomposition (SVD) is a powerful tool for multivariate analysis. However, independent computation of the SVD for each sample taken from a bandlimited matrix random process will result in singular value sample paths whose…
Text-to-image diffusion models have made significant progress in generating naturalistic images from textual inputs, and demonstrate the capacity to learn and represent complex visual-semantic relationships. While these diffusion models…
Diffusion-based models, widely used in text-to-image generation, have proven effective in 2D representation learning. Recently, this framework has been extended to 3D self-supervised learning by constructing a conditional point generator…
Diffusion models achieve remarkable fidelity in image synthesis, yet precise control over their outputs for targeted editing remains challenging. A key step toward controllability is to identify interpretable directions in the model's…
The pre-trained text-image discriminative models, such as CLIP, has been explored for open-vocabulary semantic segmentation with unsatisfactory results due to the loss of crucial localization information and awareness of object shapes.…