Search Results for author:
Found 17 papers, 7 papers with code
SynthLight: Portrait Relighting with Diffusion Model by Learning to Re-render Synthetic Faces
Our method generalizes to diverse real photographs and produces realistic illumination effects, including specular highlights and cast shadows, while preserving the subject's identity.
Text2Relight: Creative Portrait Relighting with Text Guidance
As a condition of the lighting images, we perform image-based relighting for both foreground and background using a single portrait image or a set of OLAT (One-Light-at-A-Time) images captured from lightstage system.
Generative Image Layer Decomposition with Visual Effects
Layered representations, which allow for independent editing of image components, are essential for user-driven content creation, yet existing approaches often struggle to decompose image into plausible layers with accurately retained transparent visual effects such as shadows and reflections.
Baking Gaussian Splatting into Diffusion Denoiser for Fast and Scalable Single-stage Image-to-3D Generation
Existing feed-forward image-to-3D methods mainly rely on 2D multi-view diffusion models that cannot guarantee 3D consistency.
Learning General-Purpose Biomedical Volume Representations using Randomized Synthesis
Current volumetric biomedical foundation models struggle to generalize as public 3D datasets are small and do not cover the broad diversity of medical procedures, conditions, anatomical regions, and imaging protocols.
WiCV@CVPR2024: The Thirteenth Women In Computer Vision Workshop at the Annual CVPR Conference
In this paper, we present the details of Women in Computer Vision Workshop - WiCV 2024, organized alongside the CVPR 2024 in Seattle, Washington, United States.
Generative Portrait Shadow Removal
For robust and natural shadow removal, we propose to train the diffusion model with a compositional repurposing framework: a pre-trained text-guided image generation model is first fine-tuned to harmonize the lighting and color of the foreground with a background scene by using a background harmonization dataset; and then the model is further fine-tuned to generate a shadow-free portrait image via a shadow-paired dataset.
Relightful Harmonization: Lighting-aware Portrait Background Replacement
Portrait harmonization aims to composite a subject into a new background, adjusting its lighting and color to ensure harmony with the background scene.
Microscopy Image Segmentation via Point and Shape Regularized Data Synthesis
Current deep learning-based approaches for the segmentation of microscopy images heavily rely on large amount of training data with dense annotation, which is highly costly and laborious in practice.
Improving Tuning-Free Real Image Editing with Proximal Guidance
Null-text inversion (NTI) optimizes null embeddings to align the reconstruction and inversion trajectories with larger CFG scales, enabling real image editing with cross-attention control.
Multiscale Structure Guided Diffusion for Image Deblurring
We evaluate a single-dataset trained model on diverse datasets and demonstrate more robust deblurring results with fewer artifacts on unseen data.
Local Spatiotemporal Representation Learning for Longitudinally-consistent Neuroimage Analysis
Recent self-supervised advances in medical computer vision exploit global and local anatomical self-similarity for pretraining prior to downstream tasks such as segmentation.
Q-space Conditioned Translation Networks for Directional Synthesis of Diffusion Weighted Images from Multi-modal Structural MRI
Further, such approaches can restrict downstream usage of variably sampled DWIs for usages including the estimation of microstructural indices or tractography.
Generative Adversarial Registration for Improved Conditional Deformable Templates
Deformable templates are essential to large-scale medical image registration, segmentation, and population analysis.
Segmentation-Renormalized Deep Feature Modulation for Unpaired Image Harmonization
Deep networks are now ubiquitous in large-scale multi-center imaging studies.
Structure-Attentioned Memory Network for Monocular Depth Estimation
To this end, we introduce a new Structure-Oriented Memory (SOM) module to learn and memorize the structure-specific information between RGB image domain and the depth domain.
Ranked #55 on
Monocular Depth Estimation
on KITTI Eigen split
3D-A-Nets: 3D Deep Dense Descriptor for Volumetric Shapes with Adversarial Networks
In this paper, powered with a novel design of adversarial networks (3D-A-Nets), we have developed a novel 3D deep dense shape descriptor (3D-DDSD) to address the challenging issues of efficient and effective 3D volumetric data processing.
