Related papers: NIVeL: Neural Implicit Vector Layers for Text-to-V…

Semantically consistent cross-domain image translation facilitates the generation of training data by transferring labels across different domains, making it particularly useful for plant trait identification in agriculture. However,…

Score-based diffusion models have achieved incredible performance in generating realistic images, audio, and video data. While these models produce high-quality samples with impressive details, they often introduce unrealistic artifacts,…

Text-to-image generation has witnessed significant advancements with the integration of Large Vision-Language Models (LVLMs), yet challenges remain in aligning complex textual descriptions with high-quality, visually coherent images. This…

The quality of the prompts provided to text-to-image diffusion models determines how faithful the generated content is to the user's intent, often requiring `prompt engineering'. To harness visual concepts from target images without prompt…

Learning from a large corpus of data, pre-trained models have achieved impressive progress nowadays. As popular generative pre-training, diffusion models capture both low-level visual knowledge and high-level semantic relations. In this…

Score-based diffusion models in infinite-dimensional function spaces provide a mathematically principled framework for modelling function-valued data, offering key advantages such as resolution invariance and the ability to handle irregular…

Deep generative models have shown success in generating 3D shapes with different representations. In this work, we propose Neural Volumetric Mesh Generator(NVMG) which can generate novel and high-quality volumetric meshes. Unlike the…

Diffusion models excel at generative modeling (e.g., text-to-image) but sampling requires multiple denoising network passes, limiting practicality. Efforts such as progressive distillation or consistency distillation have shown promise by…

The current success of diffusion transformers heavily depends on the compressed latent space shaped by the pre-trained variational autoencoder(VAE). However, this two-stage training paradigm inevitably introduces accumulated errors and…

Novel view synthesis (NVS) seeks to render photorealistic, 3D-consistent images of a scene from unseen camera poses given only a sparse set of posed views. Existing deterministic networks render observed regions quickly but blur unobserved…

Large-scale text-guided image diffusion models have shown astonishing results in text-to-image (T2I) generation. However, applying these models to synthesize textures for 3D geometries remains challenging due to the domain gap between 2D…

Scalable Vector Graphics (SVG) has become the de facto standard for vector graphics in digital design, offering resolution independence and precise control over individual elements. Despite their advantages, creating high-quality SVG…

A multitude of imaging and vision tasks have seen recently a major transformation by deep learning methods and in particular by the application of convolutional neural networks. These methods achieve impressive results, even for…

This paper introduces the first gradient-based framework for prompt optimization in text-to-image diffusion models. We formulate prompt engineering as a discrete optimization problem over the language space. Two major challenges arise in…

Infrared imaging is essential for autonomous driving and robotic operations as a supportive modality due to its reliable performance in challenging environments. Despite its popularity, the limitations of infrared cameras, such as low…

Text-to-Image (T2I) generation methods based on diffusion model have garnered significant attention in the last few years. Although these image synthesis methods produce visually appealing results, they frequently exhibit spelling errors…

While many unsupervised learning models focus on one family of tasks, either generative or discriminative, we explore the possibility of a unified representation learner: a model which addresses both families of tasks simultaneously. We…

Diffusion models create data from noise by inverting the forward paths of data towards noise and have emerged as a powerful generative modeling technique for high-dimensional, perceptual data such as images and videos. Rectified flow is a…

The predominant approach to advancing text-to-image generation has been training-time scaling, where larger models are trained on more data using greater computational resources. While effective, this approach is computationally expensive,…

Vector representation of sentences is important for many text processing tasks that involve clustering, classifying, or ranking sentences. Recently, distributed representation of sentences learned by neural models from unlabeled data has…