Related papers: From Editor to Dense Geometry Estimator
A great interest has arisen in using Deep Generative Models (DGM) for generative design. When assessing the quality of the generated designs, human designers focus more on structural plausibility, e.g., no missing component, rather than…
Diffusion Transformers (DiTs) are a dominant backbone for high-fidelity text-to-image generation due to strong scalability and alignment at high resolutions. However, quadratic self-attention over dense spatial tokens leads to high…
Given a partial differential equation (PDE), goal-oriented error estimation allows us to understand how errors in a diagnostic quantity of interest (QoI), or goal, occur and accumulate in a numerical approximation, for example using the…
Synthesizing images from text descriptions has become an active research area with the advent of Generative Adversarial Networks. The main goal here is to generate photo-realistic images that are aligned with the input descriptions.…
We present Deep Compression Autoencoder (DC-AE), a new family of autoencoder models for accelerating high-resolution diffusion models. Existing autoencoder models have demonstrated impressive results at a moderate spatial compression ratio…
Recent text-to-image (T2I) models have benefited from large-scale and high-quality data, demonstrating impressive performance. However, these T2I models still struggle to produce images that are aesthetically pleasing, geometrically…
Large-scale diffusion-based generative models have led to breakthroughs in text-conditioned high-resolution image synthesis. Starting from random noise, such text-to-image diffusion models gradually synthesize images in an iterative fashion…
Existing unlearning algorithms in text-to-image generative models often fail to preserve the knowledge of semantically related concepts when removing specific target concepts: a challenge known as adjacency. To address this, we propose FADE…
Professional-grade software applications are powerful but complicated$-$expert users can achieve impressive results, but novices often struggle to complete even basic tasks. Photo editing is a prime example: after loading a photo, the user…
Impressive results on real-world image super-resolution (Real-ISR) have been achieved by employing pre-trained stable diffusion (SD) models. However, one critical issue of such methods lies in their poor reconstruction of image fine…
High-quality 3D scene reconstruction has recently advanced toward generalizable feed-forward architectures, enabling the generation of complex environments in a single forward pass. However, despite their strong performance in static scene…
Mixture of Experts (MoE) pretraining is more scalable than dense Transformer pretraining, because MoEs learn to route inputs to a sparse set of their feedforward parameters. However, this means that MoEs only receive a sparse backward…
Modern Text-to-Image (T2I) generation increasingly relies on token-centric architectures that are trained with self-supervision, yet effectively fusing text with visual tokens remains a challenge. We propose \textbf{JEPA-T}, a unified…
We propose EditID, a training-free approach based on the DiT architecture, which achieves highly editable customized IDs for text to image generation. Existing text-to-image models for customized IDs typically focus more on ID consistency…
Taking advantage of the many recent advances in deep learning, text-to-image generative models currently have the merit of attracting the general public attention. Two of these models, DALL-E 2 and Imagen, have demonstrated that highly…
Recently, the strong latent Diffusion Probabilistic Model (DPM) has been applied to high-quality Text-to-Image (T2I) generation (e.g., Stable Diffusion), by injecting the encoded target text prompt into the gradually denoised diffusion…
While diffusion models excel at image synthesis, useful representations have been shown to emerge from generative pre-training, suggesting a path towards unified generative and discriminative learning. However, suboptimal semantic flow…
Demographic bias in text-to-image (T2I) generation is well studied, yet demographic-conditioned failures in instruction-guided image-to-image (I2I) editing remain underexplored. We examine whether identical edit instructions yield…
Metamaterials are emerging as a new paradigmatic material system to render unprecedented and tailorable properties for a wide variety of engineering applications. However, the inverse design of metamaterial and its multiscale system is…
Image editing aims to edit the given synthetic or real image to meet the specific requirements from users. It is widely studied in recent years as a promising and challenging field of Artificial Intelligence Generative Content (AIGC).…