Related papers: DiHuR: Diffusion-Guided Generalizable Human Recons…
We present DINAR, an approach for creating realistic rigged fullbody avatars from single RGB images. Similarly to previous works, our method uses neural textures combined with the SMPL-X body model to achieve photo-realistic quality of…
Recent advances in deep learning have shown that learning robust feature representations is critical for the success of many computer vision tasks, including medical image segmentation. In particular, both transformer and…
We propose DepR, a depth-guided single-view scene reconstruction framework that integrates instance-level diffusion within a compositional paradigm. Instead of reconstructing the entire scene holistically, DepR generates individual objects…
Recent advancements in diffusion models have significantly improved performance in super-resolution (SR) tasks. However, previous research often overlooks the fundamental differences between SR and general image generation. General image…
Diffusion priors have recently demonstrated strong capability in enhancing the quality of sparse-view 3D reconstruction by augmenting training views at novel viewpoints, but they inevitably introduce hallucinated content -- artifacts…
DiffusionAvatars synthesizes a high-fidelity 3D head avatar of a person, offering intuitive control over both pose and expression. We propose a diffusion-based neural renderer that leverages generic 2D priors to produce compelling images of…
3D reconstruction from a single image is a long-standing problem in computer vision. Learning-based methods address its inherent scale ambiguity by leveraging increasingly large labeled and unlabeled datasets, to produce geometric priors…
Capsule endoscopy has enabled minimally invasive gastrointestinal imaging, but its clinical utility is limited by the inherently low resolution of captured images due to hardware, power, and transmission constraints. This limitation hampers…
Object recognition, commonly performed by a camera, is a fundamental requirement for robots to complete complex tasks. Some tasks require recognizing objects far from the robot's camera. A challenging example is Ultra-Range Gesture…
Merging multi-exposure images is a common approach for obtaining high dynamic range (HDR) images, with the primary challenge being the avoidance of ghosting artifacts in dynamic scenes. Recent methods have proposed using deep neural…
3D human pose estimation from 2D images is a challenging problem due to depth ambiguity and occlusion. Because of these challenges the task is underdetermined, where there exists multiple -- possibly infinite -- poses that are plausible…
Single image super-resolution (SISR) aims to reconstruct high-resolution (HR) images from the given low-resolution (LR) ones, which is an ill-posed problem because one LR image corresponds to multiple HR images. Recently, learning-based…
Diffusion model (DM) has achieved SOTA performance by modeling the image synthesis process into a sequential application of a denoising network. However, different from image synthesis, image restoration (IR) has a strong constraint to…
In-bed human mesh recovery can be crucial and enabling for several healthcare applications, including sleep pattern monitoring, rehabilitation support, and pressure ulcer prevention. However, it is difficult to collect large real-world…
Image restoration (IR) has been an indispensable and challenging task in the low-level vision field, which strives to improve the subjective quality of images distorted by various forms of degradation. Recently, the diffusion model has…
Urban scene reconstruction from real-world observations has emerged as a powerful tool for self-driving development and testing. While current neural rendering approaches achieve high-fidelity rendering along the recorded trajectories,…
We present a novel approach to leverage prior knowledge encapsulated in pre-trained text-to-image diffusion models for blind super-resolution (SR). Specifically, by employing our time-aware encoder, we can achieve promising restoration…
Single-image relighting is a challenging task that involves reasoning about the complex interplay between geometry, materials, and lighting. Many prior methods either support only specific categories of images, such as portraits, or require…
Diffusion models have made significant strides in language-driven and layout-driven image generation. However, most diffusion models are limited to visible RGB image generation. In fact, human perception of the world is enriched by diverse…
Recent progress in neural rendering has brought forth pioneering methods, such as NeRF and Gaussian Splatting, which revolutionize view rendering across various domains like AR/VR, gaming, and content creation. While these methods excel at…