Search Results for author:
Found 22 papers, 11 papers with code
Neural 3D Strokes: Creating Stylized 3D Scenes with Vectorized 3D Strokes
We present Neural 3D Strokes, a novel technique to generate stylized images of a 3D scene at arbitrary novel views from multi-view 2D images.
GRIG: Few-Shot Generative Residual Image Inpainting
Image inpainting is the task of filling in missing or masked region of an image with semantically meaningful contents.
ShapeScaffolder: Structure-Aware 3D Shape Generation from Text
However, humans tend to understand both shape and text as being structure-based.
Understanding the Vulnerability of Skeleton-based Human Activity Recognition via Black-box Attack
Via BASAR, we find on-manifold adversarial samples are extremely deceitful and rather common in skeletal motions, in contrast to the common belief that adversarial samples only exist off-manifold.
Gradient-based Point Cloud Denoising with Uniformity
Point clouds captured by depth sensors are often contaminated by noises, obstructing further analysis and applications.
Parametric Reshaping of Portraits in Videos
In the second stage, we first reshape the reconstructed 3D face using a parametric reshaping model reflecting the weight change of the face, and then utilize the reshaped 3D face to guide the warping of video frames.
HairMapper: Removing Hair From Portraits Using GANs
Removing hair from portrait images is challenging due to the complex occlusions between hair and face, as well as the lack of paired portrait data with/without hair.
Geometric and Textural Augmentation for Domain Gap Reduction
Research has shown that convolutional neural networks for object recognition are vulnerable to changes in depiction because learning is biased towards the low-level statistics of texture patches.
Learning To Warp for Style Transfer
Since its inception in 2015, Style Transfer has focused on texturing a content image using an art exemplar.
Understanding the Robustness of Skeleton-based Action Recognition under Adversarial Attack
In this paper, we examine the robustness of state-of-the-art action recognizers against adversarial attack, which has been rarely investigated so far.
BASAR:Black-box Attack on Skeletal Action Recognition
The robustness of skeleton-based activity recognizers has been questioned recently, which shows that they are vulnerable to adversarial attacks when the full-knowledge of the recognizer is accessible to the attacker.
Multiple Pairwise Ranking Networks for Personalized Video Summarization
In this paper, we investigate video summarization in the supervised setting.
Low-Rank Matrix Recovery from Noise via an MDL Framework-based Atomic Norm
The recovery of the underlying low-rank structure of clean data corrupted with sparse noise/outliers is attracting increasing interest.
Spatial Information Guided Convolution for Real-Time RGBD Semantic Segmentation
S-Conv is competent to infer the sampling offset of the convolution kernel guided by the 3D spatial information, helping the convolutional layer adjust the receptive field and adapt to geometric transformations.
Ranked #20 on
Semantic Segmentation
on SUN-RGBD
(using extra training data)
BlockGAN: Learning 3D Object-aware Scene Representations from Unlabelled Images
Our experiments show that using explicit 3D features to represent objects allows BlockGAN to learn disentangled representations both in terms of objects (foreground and background) and their properties (pose and identity).
Semantic Regularization: Improve Few-shot Image Classification by Reducing Meta Shift
This strategy leads to severe meta shift issues across multiple tasks, meaning the learned prototypes or class descriptors are not stable as each task only involves their own support set.
SMART: Skeletal Motion Action Recognition aTtack
In this paper, we propose a method, SMART, to attack action recognizers which rely on 3D skeletal motions.
Rank3DGAN: Semantic mesh generation using relative attributes
In this paper, we investigate a novel problem of using generative adversarial networks in the task of 3D shape generation according to semantic attributes.
HoloGAN: Unsupervised learning of 3D representations from natural images
This shows that HoloGAN is the first generative model that learns 3D representations from natural images in an entirely unsupervised manner.
HandMap: Robust Hand Pose Estimation via Intermediate Dense Guidance Map Supervision
This work presents a novel hand pose estimation framework via intermediate dense guidance map supervision.
RenderNet: A deep convolutional network for differentiable rendering from 3D shapes
We present RenderNet, a differentiable rendering convolutional network with a novel projection unit that can render 2D images from 3D shapes.
Physics-driven Fire Modeling from Multi-view Images
This allows for a number of novel phenomena such as global fire illumination effects.
