Search Results for author:
Found 22 papers, 13 papers with code
RAGDiffusion: Faithful Cloth Generation via External Knowledge Assimilation
Standard clothing asset generation involves creating forward-facing flat-lay garment images displayed on a clear background by extracting clothing information from diverse real-world contexts, which presents significant challenges due to highly standardized sampling distributions and precise structural requirements in the generated images.
AnyFit: Controllable Virtual Try-on for Any Combination of Attire Across Any Scenario
While image-based virtual try-on has made significant strides, emerging approaches still fall short of delivering high-fidelity and robust fitting images across various scenarios, as their models suffer from issues of ill-fitted garment styles and quality degrading during the training process, not to mention the lack of support for various combinations of attire.
Potential Paradigm Shift in Hazard Risk Management: AI-Based Weather Forecast for Tropical Cyclone Hazards
The advents of Artificial Intelligence (AI)-driven models marks a paradigm shift in risk management strategies for meteorological hazards.
Toward Tiny and High-quality Facial Makeup with Data Amplify Learning
The core idea of DAL lies in employing a Diffusion-based Data Amplifier (DDA) to "amplify" limited images for the model training, thereby enabling accurate pixel-to-pixel supervision with merely a handful of annotations.
Towards High-fidelity Artistic Image Vectorization via Texture-Encapsulated Shape Parameterization
We develop a novel vectorized image representation scheme accommodating both shape/geometry and texture in a decoupled way particularly tailored for reconstruction and editing tasks of artistic/design images such as Emojis and Cliparts.
Vector Graphics Generation via Mutually Impulsed Dual-domain Diffusion
Intelligent generation of vector graphics has very promising applications in the fields of advertising and logo design artistic painting animation production etc.
FocalDreamer: Text-driven 3D Editing via Focal-fusion Assembly
While text-3D editing has made significant strides in leveraging score distillation sampling, emerging approaches still fall short in delivering separable, precise and consistent outcomes that are vital to content creation.
Omni Aggregation Networks for Lightweight Image Super-Resolution
While lightweight ViT framework has made tremendous progress in image super-resolution, its uni-dimensional self-attention modeling, as well as homogeneous aggregation scheme, limit its effective receptive field (ERF) to include more comprehensive interactions from both spatial and channel dimensions.
3DQD: Generalized Deep 3D Shape Prior via Part-Discretized Diffusion Process
We develop a generalized 3D shape generation prior model, tailored for multiple 3D tasks including unconditional shape generation, point cloud completion, and cross-modality shape generation, etc.
Deep Arbitrary-Scale Image Super-Resolution via Scale-Equivariance Pursuit
The ability of scale-equivariance processing blocks plays a central role in arbitrary-scale image super-resolution tasks.
Generalized Deep 3D Shape Prior via Part-Discretized Diffusion Process
We develop a generalized 3D shape generation prior model, tailored for multiple 3D tasks including unconditional shape generation, point cloud completion, and cross-modality shape generation, etc.
Editable Image Geometric Abstraction via Neural Primitive Assembly
This work explores a novel image geometric abstraction paradigm based on assembly out of a pool of pre-defined simple parametric primitives (i. e., triangle, rectangle, circle and semicircle), facilitating controllable shape editing in images.
Learning Continuous Depth Representation via Geometric Spatial Aggregator
Depth map super-resolution (DSR) has been a fundamental task for 3D computer vision.
Im2Oil: Stroke-Based Oil Painting Rendering with Linearly Controllable Fineness Via Adaptive Sampling
Comparison with existing state-of-the-art oil painting techniques shows that our results have higher fidelity and more realistic textures.
RainNet: A Large-Scale Imagery Dataset for Spatial Precipitation Downscaling
Spatial precipitation downscaling is one of the most important meteorological problems.
SimSwap: An Efficient Framework For High Fidelity Face Swapping
In contrast to previous approaches that either lack the ability to generalize to arbitrary identity or fail to preserve attributes like facial expression and gaze direction, our framework is capable of transferring the identity of an arbitrary source face into an arbitrary target face while preserving the attributes of the target face.
Ranked #2 on
Face Swapping
on FaceForensics++
X-volution: On the unification of convolution and self-attention
Convolution and self-attention are acting as two fundamental building blocks in deep neural networks, where the former extracts local image features in a linear way while the latter non-locally encodes high-order contextual relationships.
Ranked #83 on
Instance Segmentation
on COCO minival
Image Translation via Fine-grained Knowledge Transfer
Extensive experiments well demonstrate the effectiveness and feasibility of our framework in different image-translation tasks.
RainNet: A Large-Scale Imagery Dataset and Benchmark for Spatial Precipitation Downscaling
To alleviate these obstacles, we present the first large-scale spatial precipitation downscaling dataset named RainNet, which contains more than $62, 400$ pairs of high-quality low/high-resolution precipitation maps for over $17$ years, ready to help the evolution of deep learning models in precipitation downscaling.
Sketch Generation with Drawing Process Guided by Vector Flow and Grayscale
Existing pencil sketch algorithms are based on texture rendering rather than the direct imitation of strokes, making them unable to show the drawing process but only a final result.
CooGAN: A Memory-Efficient Framework for High-Resolution Facial Attribute Editing
In contrast to great success of memory-consuming face editing methods at a low resolution, to manipulate high-resolution (HR) facial images, i. e., typically larger than 7682 pixels, with very limited memory is still challenging.
Anisotropic Stroke Control for Multiple Artists Style Transfer
Furthermore, the results are with distinctive artistic style and retain the anisotropic semantic information.
