Search Results for author:
Found 33 papers, 15 papers with code
Erasing Appearance Preservation in Optimization-based Smoothing
We show that partially ""erasing"" the appearance preservation facilitate adequate image smoothing.
ViewCrafter: Taming Video Diffusion Models for High-fidelity Novel View Synthesis
Our method takes advantage of the powerful generation capabilities of video diffusion model and the coarse 3D clues offered by point-based representation to generate high-quality video frames with precise camera pose control.
ToonCrafter: Generative Cartoon Interpolation
We introduce ToonCrafter, a novel approach that transcends traditional correspondence-based cartoon video interpolation, paving the way for generative interpolation.
Physics-based Scene Layout Generation from Human Motion
To attain plausible and realistic interaction motions, our method explicitly introduces physical constraints.
Sketch2Manga: Shaded Manga Screening from Sketch with Diffusion Models
Unfortunately, there is no existing method that tailors for automatic manga screening, probably due to the difficulty of generating high-quality shaded high-frequency screentones.
Highly Detailed and Temporal Consistent Video Stylization via Synchronized Multi-Frame Diffusion
However, they struggle to generate videos with both highly detailed appearance and temporal consistency.
Text-Guided Texturing by Synchronized Multi-View Diffusion
In this paper, we propose a synchronized multi-view diffusion approach that allows the diffusion processes from different views to reach a consensus of the generated content early in the process, and hence ensures the texture consistency.
DynamiCrafter: Animating Open-domain Images with Video Diffusion Priors
Animating a still image offers an engaging visual experience.
BroadCAM: Outcome-agnostic Class Activation Mapping for Small-scale Weakly Supervised Applications
Class activation mapping~(CAM), a visualization technique for interpreting deep learning models, is now commonly used for weakly supervised semantic segmentation~(WSSS) and object localization~(WSOL).
Object Localization
Weakly supervised Semantic Segmentation
+1
Taming Reversible Halftoning via Predictive Luminance
Furthermore, to tackle the conflicts between the blue-noise quality and restoration accuracy in our novel base method, we proposed a predictor-embedded approach to offload predictable information from the network, which in our case is the luminance information resembling from the halftone pattern.
Manga Rescreening with Interpretable Screentone Representation
To overcome these limitations, we propose a novel interpretable representation of screentones that disentangles their intensity and type features, enabling better recognition and synthesis of screentones.
Video Colorization with Pre-trained Text-to-Image Diffusion Models
In this paper, we present ColorDiffuser, an adaptation of a pre-trained text-to-image latent diffusion model for video colorization.
Make-Your-Video: Customized Video Generation Using Textual and Structural Guidance
Our method, dubbed Make-Your-Video, involves joint-conditional video generation using a Latent Diffusion Model that is pre-trained for still image synthesis and then promoted for video generation with the introduction of temporal modules.
Improved Diffusion-based Image Colorization via Piggybacked Models
Our key idea is to exploit the color prior knowledge in the pre-trained T2I diffusion model for realistic and diverse colorization.
CodeTalker: Speech-Driven 3D Facial Animation with Discrete Motion Prior
In this paper, we propose to cast speech-driven facial animation as a code query task in a finite proxy space of the learned codebook, which effectively promotes the vividness of the generated motions by reducing the cross-modal mapping uncertainty.
Ranked #4 on
3D Face Animation
on BEAT2
Disentangled Image Colorization via Global Anchors
Our key insight is that several carefully located anchors could approximately represent the color distribution of an image, and conditioned on the anchor colors, we can predict the image color in a deterministic manner by utilizing internal correlation.
Pseudo Bias-Balanced Learning for Debiased Chest X-ray Classification
Deep learning models were frequently reported to learn from shortcuts like dataset biases.
Screentone-Preserved Manga Retargeting
Fortunately, the rescaled manga shares the same region-wise screentone correspondences with the original manga, which enables us to simplify the screentone synthesis problem as an anchor-based proposals selection and rearrangement problem.
Point Set Self-Embedding
To achieve a learnable self-embedding scheme, we design a novel framework with two jointly-trained networks: one to encode the input point set into its self-embedded sparse point set and the other to leverage the embedded information for inverting the original point set back.
Scale-arbitrary Invertible Image Downscaling
In this paper, we propose a scale-Arbitrary Invertible image Downscaling Network (AIDN), to natively downscale HR images with arbitrary scale factors.
Neural Recognition of Dashed Curves With Gestalt Law of Continuity
While humans can intuitively recognize dashed curves from disjoint curve segments based on the law of continuity in Gestalt psychology, it is extremely difficult for computers to model the Gestalt law of continuity and recognize the dashed curves since high-level semantic understanding is needed for this task.
Invertible Tone Mapping with Selectable Styles
In this paper, we propose an invertible tone mapping method that converts the multi-exposure HDR to a true LDR (8-bit per color channel) and reserves the capability to accurately restore the original HDR from this {\em invertible LDR}.
Conditional Directed Graph Convolution for 3D Human Pose Estimation
Based on this representation, we further propose a spatial-temporal conditional directed graph convolution to leverage varying non-local dependence for different poses by conditioning the graph topology on input poses.
Ranked #17 on
3D Human Pose Estimation
on Human3.6M
User-Guided Line Art Flat Filling With Split Filling Mechanism
We present a deep learning framework for user-guided line art flat filling that can compute the "influence areas" of the user color scribbles, i. e., the areas where the user scribbles should propagate and influence.
Exploiting Aliasing for Manga Restoration
First, we predict the target resolution from the degraded manga via the Scale Estimation Network (SE-Net) with spatial voting scheme.
Bidirectional Projection Network for Cross Dimension Scene Understanding
Via the \emph{BPM}, complementary 2D and 3D information can interact with each other in multiple architectural levels, such that advantages in these two visual domains can be combined for better scene recognition.
Ranked #19 on
Semantic Segmentation
on ScanNet
A Learned Compact and Editable Light Field Representation
Light fields are 4D scene representation typically structured as arrays of views, or several directional samples per pixel in a single view.
Deep Halftoning With Reversible Binary Pattern
Existing halftoning algorithms usually drop colors and fine details when dithering color images with binary dot patterns, which makes it extremely difficult to recover the original information.
Enhance Convolutional Neural Networks with Noise Incentive Block
Noise Incentive Block (NIB), which serves as a generic plug-in for any CNN generation model.
Mononizing Binocular Videos
This paper presents the idea ofmono-nizingbinocular videos and a frame-work to effectively realize it.
Image and Video Processing Graphics
Binocular Tone Mapping with Improved Overall Contrast and Local Details
However, the existing research lacks the binocular perception study and is unable to generate the optimal binocular pair that presents the most visual content.
Real-time Deep Video Deinterlacing
Interlacing is a widely used technique, for television broadcast and video recording, to double the perceived frame rate without increasing the bandwidth.
Ranked #11 on
Video Deinterlacing
on MSU Deinterlacer Benchmark
ENFT: Efficient Non-Consecutive Feature Tracking for Robust Structure-from-Motion
Our framework consists of steps of solving the feature `dropout' problem when indistinctive structures, noise or large image distortion exists, and of rapidly recognizing and joining common features located in different subsequences.
