Related papers: MADFormer: Mixed Autoregressive and Diffusion Tran…
Multi-focus image fusion aims to generate an all-in-focus image from a sequence of partially focused input images. Existing fusion algorithms generally assume that, for every spatial location in the scene, there is at least one input image…
We introduce a novel diffusion transformer, LazyDiffusion, that generates partial image updates efficiently. Our approach targets interactive image editing applications in which, starting from a blank canvas or an image, a user specifies a…
Diffusion models have become a mainstream approach for high-resolution image synthesis. However, directly generating higher-resolution images from pretrained diffusion models will encounter unreasonable object duplication and exponentially…
Understanding and modeling lighting effects are fundamental tasks in computer vision and graphics. Classic physically-based rendering (PBR) accurately simulates the light transport, but relies on precise scene representations--explicit 3D…
Large-scale diffusion models have achieved remarkable success in generating high-quality images from textual descriptions, gaining popularity across various applications. However, the generation of layered content, such as transparent…
Reliable perception is essential for autonomous driving systems to operate safely under diverse real-world traffic conditions. However, camera- and LiDAR-based perception systems suffer from performance degradation under adverse weather and…
We propose SDAR, a Synergistic Diffusion-Autoregression paradigm that unifies the training efficiency of autoregressive models with the parallel inference capability of diffusion. Instead of costly end-to-end diffusion training, SDAR…
Deep learning-based image fusion approaches have obtained wide attention in recent years, achieving promising performance in terms of visual perception. However, the fusion module in the current deep learning-based methods suffers from two…
Recent generative models show impressive results in photo-realistic image generation. However, artifacts often inevitably appear in the generated results, leading to downgraded user experience and reduced performance in downstream tasks.…
Multi-sensor modal fusion has demonstrated strong advantages in 3D object detection tasks. However, existing methods that fuse multi-modal features require transforming features into the bird's eye view space and may lose certain…
Image classification serves as the cornerstone of computer vision, traditionally achieved through discriminative models based on deep neural networks. Recent advancements have introduced classification methods derived from generative…
Multimodal variational autoencoders have demonstrated their ability to learn the relationships between different modalities by mapping them into a latent representation. Their design and capacity to perform any-to-any conditional and…
Recent advances in diffusion models have driven remarkable progress in image generation. However, the generation process remains computationally intensive, and users often need to iteratively refine prompts to achieve the desired results,…
Discriminative classifiers have become a foundational tool in deep learning for medical imaging, excelling at learning separable features of complex data distributions. However, these models often need careful design, augmentation, and…
In this study, we aim to enhance the capabilities of diffusion-based text-to-image (T2I) generation models by integrating diverse modalities beyond textual descriptions within a unified framework. To this end, we categorize widely used…
The success of deep learning in computer vision over the past decade has hinged on large labeled datasets and strong pretrained models. In data-scarce settings, the quality of these pretrained models becomes crucial for effective transfer…
Autoregressive models (ARMs) and diffusion models (DMs) represent two leading paradigms in generative modeling, each excelling in distinct areas: ARMs in global context modeling and long-sequence generation, and DMs in generating…
Diffusion models have become central to various image editing tasks, yet they often fail to fully adhere to physical laws, particularly with effects like shadows, reflections, and occlusions. In this work, we address the challenge of…
Enabling image generation models to be spatially controlled is an important area of research, empowering users to better generate images according to their own fine-grained specifications via e.g. edge maps, poses. Although this task has…
In spite of recent progress, image diffusion models still produce artifacts. A common solution is to leverage the feedback provided by quality assessment systems or human annotators to optimize the model, where images are generally rated in…