Related papers: From Editor to Dense Geometry Estimator

Adapting pretrained diffusion-based generative models for text-driven image editing with negligible tuning overhead has demonstrated remarkable potential. A classical adaptation paradigm, as followed by these methods, first infers the…

Text-guided image editing using Text-to-Image (T2I) models often fails to yield satisfactory results, frequently introducing unintended modifications, such as the loss of local detail and color changes. In this paper, we analyze these…

Model editing offers a low-cost technique to inject or correct a particular behavior in a pre-trained model without extensive retraining, supporting applications such as factual correction and bias mitigation. Despite this common practice,…

Latent diffusion models have established a new state-of-the-art in high-resolution visual generation. Integrating Vision Foundation Model priors improves generative efficiency, yet existing latent designs remain largely heuristic. These…

Multi-task learning (MTL) for dense prediction has shown promising results but still faces challenges in balancing shared representations with task-specific specialization. In this paper, we introduce a novel Fine-Grained Mixture of Experts…

Recent advances in discriminative and generative pretraining have yielded geometry estimation models with strong generalization capabilities. While discriminative monocular geometry estimation methods rely on large-scale fine-tuning data to…

Gigantic pre-trained models have become central to natural language processing (NLP), serving as the starting point for fine-tuning towards a range of downstream tasks. However, two pain points persist for this paradigm: (a) as the…

Dense semantic forecasting anticipates future events in video by inferring pixel-level semantics of an unobserved future image. We present a novel approach that is applicable to various single-frame architectures and tasks. Our approach…

Many modern applications involve predicting structured, non-Euclidean outputs such as probability distributions, networks, and symmetric positive-definite matrices. These outputs are naturally modeled as elements of general metric spaces,…

Recent advances in diffusion models have enabled high-quality image generation, leading to increasing demand for post-generation editing that modifies local regions while preserving global structure. Achieving such flexible and precise…

Editing real images using a pre-trained text-to-image (T2I) diffusion/flow model often involves inverting the image into its corresponding noise map. However, inversion by itself is typically insufficient for obtaining satisfactory results,…

Latent generative models have emerged as a leading approach for high-quality image synthesis. These models rely on an autoencoder to compress images into a latent space, followed by a generative model to learn the latent distribution. We…

Large-scale Text-to-Image (T2I) diffusion models have revolutionized image generation over the last few years. Although owning diverse and high-quality generation capabilities, translating these abilities to fine-grained image editing…

Text-to-image (T2I) generation has seen significant progress with diffusion models, enabling generation of photo-realistic images from text prompts. Despite this progress, existing methods still face challenges in following complex text…

Objective: Radiotherapy uses precise doses of radiation to treat cancer, requiring accurate verification, e.g. using the Electronic Portal Imaging Device (EPID), to guide treatment. To develop an effective artificial intelligence (AI) model…

By pretraining to synthesize coherent images from perturbed inputs, generative models inherently learn to understand object boundaries and scene compositions. How can we repurpose these generative representations for general-purpose…

Diffusion models have shown remarkable capabilities in generating high quality and creative images conditioned on text. An interesting application of such models is structure preserving text guided image editing. Existing approaches rely on…

Diffusion models have established themselves as the de facto primary paradigm in visual generative modeling, revolutionizing the field through remarkable success across various diverse applications ranging from high-quality image synthesis…

Contents generated by recent advanced Text-to-Image (T2I) diffusion models are sometimes too imaginative for existing off-the-shelf dense predictors to estimate due to the immitigable domain gap. We introduce DMP, a pipeline utilizing…

With the rapid development of diffusion models, text-to-image(T2I) models have made significant progress, showcasing impressive abilities in prompt following and image generation. Recently launched models such as FLUX.1 and Ideogram2.0,…