Search Results for author:
Found 32 papers, 20 papers with code
Autoregressive Queries for Adaptive Tracking with Spatio-TemporalTransformers
Firstly, we introduce a set of learnable and autoregressive queries to capture the instantaneous target appearance changes in a sliding window fashion.
End-to-End Human Instance Matting
Finally, an instance matting network decodes the image features and united semantics guidance to predict all instance-level alpha mattes.
Dual-Context Aggregation for Universal Image Matting
However, existing matting methods are designed for specific objects or guidance, neglecting the common requirement of aggregating global and local contexts in image matting.
Ranked #3 on
Image Matting
on Distinctions-646
Explicit Visual Prompts for Visual Object Tracking
Specifically, we utilize spatio-temporal tokens to propagate information between consecutive frames without focusing on updating templates.
ODTrack: Online Dense Temporal Token Learning for Visual Tracking
To alleviate the above problem, we propose a simple, flexible and effective video-level tracking pipeline, named \textbf{ODTrack}, which densely associates the contextual relationships of video frames in an online token propagation manner.
Ranked #1 on
Visual Object Tracking
on TrackingNet
Semi-Supervised Video Object Segmentation
Visual Object Tracking
+1
SpectralNeRF: Physically Based Spectral Rendering with Neural Radiance Field
We modify the classical spectral rendering into two main steps, 1) the generation of a series of spectrum maps spanning different wavelengths, 2) the combination of these spectrum maps for the RGB output.
MonoGaussianAvatar: Monocular Gaussian Point-based Head Avatar
In response to these challenges, we propose MonoGaussianAvatar (Monocular Gaussian Point-based Head Avatar), a novel approach that harnesses 3D Gaussian point representation coupled with a Gaussian deformation field to learn explicit head avatars from monocular portrait videos.
GPS-Gaussian: Generalizable Pixel-wise 3D Gaussian Splatting for Real-time Human Novel View Synthesis
We present a new approach, termed GPS-Gaussian, for synthesizing novel views of a character in a real-time manner.
GaussianAvatar: Towards Realistic Human Avatar Modeling from a Single Video via Animatable 3D Gaussians
We present GaussianAvatar, an efficient approach to creating realistic human avatars with dynamic 3D appearances from a single video.
CaPhy: Capturing Physical Properties for Animatable Human Avatars
In contrast to previous work on 3D avatar reconstruction, our method is able to generalize to novel poses with realistic dynamic cloth deformations.
ProxyCap: Real-time Monocular Full-body Capture in World Space via Human-Centric Proxy-to-Motion Learning
For more accurate and physically plausible predictions in world space, our network is designed to learn human motions from a human-centric perspective, which enables the understanding of the same motion captured with different camera trajectories.
Ranked #208 on
3D Human Pose Estimation
on Human3.6M
Learning Geometric Transformation for Point Cloud Completion
It exploits the repetitive geometric structures in common 3D objects to recover the complete shapes, which contains three sub-networks: geometric patch network, structure transformation network, and detail refinement network.
Ranked #4 on
Point Cloud Completion
on ShapeNet
Rethinking Context Aggregation in Natural Image Matting
For natural image matting, context information plays a crucial role in estimating alpha mattes especially when it is challenging to distinguish foreground from its background.
Ranked #1 on
Image Matting
on Composition-1K
Long-Range Feature Propagating for Natural Image Matting
Finally, we use the matting module which takes the image, trimap and context features to estimate the alpha matte.
Ranked #6 on
Image Matting
on Composition-1K
(using extra training data)
Distractor-Aware Fast Tracking via Dynamic Convolutions and MOT Philosophy
A practical long-term tracker typically contains three key properties, i. e. an efficient model design, an effective global re-detection strategy and a robust distractor awareness mechanism.
Efficient Regional Memory Network for Video Object Segmentation
For the current query frame, the query regions are tracked and predicted based on the optical flow estimated from the previous frame.
Continuous Prediction of Lower-Limb Kinematics From Multi-Modal Biomedical Signals
Challenges of exoskeletons motor intent decoding schemes remain in making a continuous prediction to compensate for the hysteretic response caused by mechanical transmission.
Object-and-Action Aware Model for Visual Language Navigation
The first is object description (e. g., 'table', 'door'), each presenting as a tip for the agent to determine the next action by finding the item visible in the environment, and the second is action specification (e. g., 'go straight', 'turn left') which allows the robot to directly predict the next movements without relying on visual perceptions.
Pix2Vox++: Multi-scale Context-aware 3D Object Reconstruction from Single and Multiple Images
A multi-scale context-aware fusion module is then introduced to adaptively select high-quality reconstructions for different parts from all coarse 3D volumes to obtain a fused 3D volume.
Ranked #3 on
3D Object Reconstruction
on Data3D−R2N2
GRNet: Gridding Residual Network for Dense Point Cloud Completion
In particular, we devise two novel differentiable layers, named Gridding and Gridding Reverse, to convert between point clouds and 3D grids without losing structural information.
Ranked #3 on
Point Cloud Completion
on Completion3D
Scene Text Recognition via Transformer
Different from previous transformer based models [56, 34], which just use the decoder of the transformer to decode the convolutional attention, the proposed method use a convolutional feature maps as word embedding input into transformer.
Siamese Box Adaptive Network for Visual Tracking
Most of the existing trackers usually rely on either a multi-scale searching scheme or pre-defined anchor boxes to accurately estimate the scale and aspect ratio of a target.
Toward 3D Object Reconstruction from Stereo Images
Inferring the 3D shape of an object from an RGB image has shown impressive results, however, existing methods rely primarily on recognizing the most similar 3D model from the training set to solve the problem.
Sketch-Specific Data Augmentation for Freehand Sketch Recognition
Conventional methods for this task often rely on the availability of the temporal order of sketch strokes, additional cues acquired from different modalities and supervised augmentation of sketch datasets with real images, which also limit the applicability and feasibility of these methods in real scenarios.
Light Field Saliency Detection with Deep Convolutional Networks
Light field imaging presents an attractive alternative to RGB imaging because of the recording of the direction of the incoming light.
DeepIlluminance: Contextual Illuminance Estimation via Deep Neural Networks
First, the contextual net with a center-surround architecture extracts local contextual features from image patches, and generates initial illuminant estimates and the corresponding color corrected patches.
Pix2Vox: Context-aware 3D Reconstruction from Single and Multi-view Images
Then, a context-aware fusion module is introduced to adaptively select high-quality reconstructions for each part (e. g., table legs) from different coarse 3D volumes to obtain a fused 3D volume.
Ranked #4 on
3D Object Reconstruction
on Data3D−R2N2
Convolutional Neural Networks based Intra Prediction for HEVC
To overcome this problem, in this paper, an intra prediction convolutional neural network (IPCNN) is proposed for intra prediction, which exploits the rich context of the current block and therefore is capable of improving the accuracy of predicting the current block.
An efficient deep convolutional laplacian pyramid architecture for CS reconstruction at low sampling ratios
To address this problem, we propose a deep convolutional Laplacian Pyramid Compressed Sensing Network (LapCSNet) for CS, which consists of a sampling sub-network and a reconstruction sub-network.
Ranked #1 on
Compressive Sensing
on Set5
Deep Networks for Compressed Image Sensing
First of all, we train a sampling matrix via the network training instead of using a traditional manually designed one, which is much appropriate for our deep network based reconstruct process.
Sparse vs. Non-sparse: Which One Is Better for Practical Visual Tracking?
Recently, sparse representation based visual tracking methods have attracted increasing attention in the computer vision community.
Hedged Deep Tracking
In recent years, several methods have been developed to utilize hierarchical features learned from a deep convolutional neural network (CNN) for visual tracking.
