Related papers: MatLat: Material Latent Space for PBR Texture Gene…

We propose a composable framework for latent space image augmentation that allows for easy combination of multiple augmentations. Image augmentation has been shown to be an effective technique for improving the performance of a wide variety…

We present SeamlessGAN, a method capable of automatically generating tileable texture maps from a single input exemplar. In contrast to most existing methods, focused solely on solving the synthesis problem, our work tackles both problems,…

We present a training-free approach for controllable 3D inpainting based on initial noise optimization. In the structured 3D latent diffusion framework, we observe that the underlying geometric structure is established during the early…

We present LayerDiffuse, an approach enabling large-scale pretrained latent diffusion models to generate transparent images. The method allows generation of single transparent images or of multiple transparent layers. The method learns a…

Recently, the surge of efficient and automated 3D AI-generated content (AIGC) methods has increasingly illuminated the path of transforming human imagination into complex 3D structures. However, the automated generation of 3D content is…

In this paper, we propose LSRNA, a novel framework for higher-resolution (exceeding 1K) image generation using diffusion models by leveraging super-resolution directly in the latent space. Existing diffusion models struggle with scaling…

In this paper, we show that the performance of a learnt generative model is closely related to the model's ability to accurately represent the inferred \textbf{latent data distribution}, i.e. its topology and structural properties. We…

Shape priors have long been known to be effective when reconstructing 3D shapes from noisy or incomplete data. When using a deep-learning based shape representation, this often involves learning a latent representation, which can be either…

Text-guided domain adaptation and generation of 3D-aware portraits find many applications in various fields. However, due to the lack of training data and the challenges in handling the high variety of geometry and appearance, the existing…

While diffusion models excel at generating high-quality images from text prompts, they struggle with visual consistency when generating image sequences. Existing methods generate each image independently, leading to disjointed narratives -…

Reducing token count is crucial for efficient training and inference of latent diffusion models, especially at high resolution. A common strategy is to build high-compression image tokenizers with more channels per token. However, when…

Discrete Diffusion Language Models have emerged as a compelling paradigm for unified multimodal generation, yet their deployment is hindered by high inference latency arising from iterative decoding. Existing acceleration strategies often…

Deep generative models are proficient in generating realistic data but struggle with producing rare samples in low density regions due to their scarcity of training datasets and the mode collapse problem. While recent methods aim to improve…

The recent use of diffusion prior, enhanced by pre-trained text-image models, has markedly elevated the performance of image super-resolution (SR). To alleviate the huge computational cost required by pixel-based diffusion SR, latent-based…

High-resolution 3D object generation remains a challenging task primarily due to the limited availability of comprehensive annotated training data. Recent advancements have aimed to overcome this constraint by harnessing image generative…

While language reasoning models excel in many tasks, visual reasoning remains challenging for current large multimodal models (LMMs). As a result, most LMMs default to verbalizing perceptual content into text, a strong limitation for tasks…

Topology optimization enables the automated design of efficient structures by optimally distributing material within a defined domain. However, traditional gradient-based methods often scale poorly with increasing resolution and…

Novel photo-realistic texture synthesis is an important task for generating novel scenes, including asset generation for 3D simulations. However, to date, these methods predominantly generate textured objects in 2D space. If we rely on 2D…

Modeling 3D articulated objects with realistic geometry, textures, and kinematics is essential for a wide range of applications. However, existing optimization-based reconstruction methods often require dense multi-view inputs and expensive…

Modern Latent Diffusion Models (LDMs) typically operate in low-level Variational Autoencoder (VAE) latent spaces that are primarily optimized for pixel-level reconstruction. To unify vision generation and understanding, a burgeoning trend…