Search Results for author:
Found 40 papers, 20 papers with code
Theoretically Achieving Continuous Representation of Oriented Bounding Boxes
Considerable efforts have been devoted to Oriented Object Detection (OOD).
CharacterGen: Efficient 3D Character Generation from Single Images with Multi-View Pose Canonicalization
In the field of digital content creation, generating high-quality 3D characters from single images is challenging, especially given the complexities of various body poses and the issues of self-occlusion and pose ambiguity.
Semantic-Aware Transformation-Invariant RoI Align
In this paper, we propose a novel RoI feature extractor, termed Semantic RoI Align (SRA), which is capable of extracting invariant RoI features under a variety of transformations for two-stage detectors.
DiffFacto: Controllable Part-Based 3D Point Cloud Generation with Cross Diffusion
We propose a factorization that models independent part style and part configuration distributions and presents a novel cross-diffusion network that enables us to generate coherent and plausible shapes under our proposed factorization.
Long Range Pooling for 3D Large-Scale Scene Understanding
To achieve the above properties, we propose a simple yet effective long range pooling (LRP) module using dilation max pooling, which provides a network with a large adaptive receptive field.
SegNeXt: Rethinking Convolutional Attention Design for Semantic Segmentation
Notably, SegNeXt outperforms EfficientNet-L2 w/ NAS-FPN and achieves 90. 6% mIoU on the Pascal VOC 2012 test leaderboard using only 1/10 parameters of it.
Ranked #1 on
Semantic Segmentation
on iSAID
DeepPortraitDrawing: Generating Human Body Images from Freehand Sketches
Researchers have explored various ways to generate realistic images from freehand sketches, e. g., for objects and human faces.
Visual Attention Network
In this paper, we propose a novel linear attention named large kernel attention (LKA) to enable self-adaptive and long-range correlations in self-attention while avoiding its shortcomings.
Ranked #1 on
Panoptic Segmentation
on COCO panoptic
NeRF-SR: High-Quality Neural Radiance Fields using Supersampling
We present NeRF-SR, a solution for high-resolution (HR) novel view synthesis with mostly low-resolution (LR) inputs.
CIRCLE: Convolutional Implicit Reconstruction and Completion for Large-scale Indoor Scene
We present CIRCLE, a framework for large-scale scene completion and geometric refinement based on local implicit signed distance functions.
Multiway Non-rigid Point Cloud Registration via Learned Functional Map Synchronization
We present SyNoRiM, a novel way to jointly register multiple non-rigid shapes by synchronizing the maps relating learned functions defined on the point clouds.
Attention Mechanisms in Computer Vision: A Survey
Humans can naturally and effectively find salient regions in complex scenes.
Sampling Equivariant Self-attention Networks for Object Detection in Aerial Images
Sampling equivariant networks can adjust sampling from input feature maps according to the transformation of the object, allowing a kernel to extract features of an object under different transformations.
Subdivision-Based Mesh Convolution Networks
Meshes with arbitrary connectivity can be remeshed to have Loop subdivision sequence connectivity via self-parameterization, making SubdivNet a general approach.
Can Attention Enable MLPs To Catch Up With CNNs?
In the first week of May, 2021, researchers from four different institutions: Google, Tsinghua University, Oxford University and Facebook, shared their latest work [16, 7, 12, 17] on arXiv. org almost at the same time, each proposing new learning architectures, consisting mainly of linear layers, claiming them to be comparable, or even superior to convolutional-based models.
Recursive-NeRF: An Efficient and Dynamically Growing NeRF
Only query coordinates with high uncertainties are forwarded to the next level to a bigger neural network with a more powerful representational capability.
Beyond Self-attention: External Attention using Two Linear Layers for Visual Tasks
Attention mechanisms, especially self-attention, have played an increasingly important role in deep feature representation for visual tasks.
Ranked #16 on
Semantic Segmentation
on PASCAL VOC 2012 test
MultiBodySync: Multi-Body Segmentation and Motion Estimation via 3D Scan Synchronization
We present MultiBodySync, a novel, end-to-end trainable multi-body motion segmentation and rigid registration framework for multiple input 3D point clouds.
PCT: Point cloud transformer
It is inherently permutation invariant for processing a sequence of points, making it well-suited for point cloud learning.
Ranked #2 on
3D Point Cloud Classification
on IntrA
DI-Fusion: Online Implicit 3D Reconstruction with Deep Priors
Previous online 3D dense reconstruction methods struggle to achieve the balance between memory storage and surface quality, largely due to the usage of stagnant underlying geometry representation, such as TSDF (truncated signed distance functions) or surfels, without any knowledge of the scene priors.
Alternating ConvLSTM: Learning Force Propagation with Alternate State Updates
Experimental results show that Alt-ConvLSTM efficiently models the material kinetic features and greatly outperforms vanilla ConvLSTM with only the single state update.
ClusterVO: Clustering Moving Instances and Estimating Visual Odometry for Self and Surroundings
We present ClusterVO, a stereo Visual Odometry which simultaneously clusters and estimates the motion of both ego and surrounding rigid clusters/objects.
Shallow2Deep: Indoor Scene Modeling by Single Image Understanding
Particularly, we design a shallow-to-deep architecture on the basis of convolutional networks for semantic scene understanding and modeling.
Morphing and Sampling Network for Dense Point Cloud Completion
3D point cloud completion, the task of inferring the complete geometric shape from a partial point cloud, has been attracting attention in the community.
Ranked #8 on
Point Cloud Completion
on ShapeNet
Example-Guided Style Consistent Image Synthesis from Semantic Labeling
Example-guided image synthesis aims to synthesize an image from a semantic label map and an exemplary image indicating style.
FaceShapeGene: A Disentangled Shape Representation for Flexible Face Image Editing
On the basis of the FaceShapeGene, a novel part-wise face image editing system is developed, which contains a shape-remix network and a conditional label-to-face transformer.
What and Where: A Context-based Recommendation System for Object Insertion
In this work, we propose a novel topic consisting of two dual tasks: 1) given a scene, recommend objects to insert, 2) given an object category, retrieve suitable background scenes.
TZC: Efficient Inter-Process Communication for Robotics Middleware with Partial Serialization
We show that by using TZC, the braking distance can be shortened by 16% than ROS.
Robotics
Temporally Coherent Video Harmonization Using Adversarial Networks
Since existing video datasets which have ground-truth foreground masks and optical flows are not sufficiently large, we propose a simple yet efficient method to build up a synthetic dataset supporting supervised training of the proposed adversarial network.
Learning to Reconstruct High-quality 3D Shapes with Cascaded Fully Convolutional Networks
We present a data-driven approach to reconstructing high-resolution and detailed volumetric representations of 3D shapes.
Associating Inter-Image Salient Instances for Weakly Supervised Semantic Segmentation
We also combine our method with Mask R-CNN for instance segmentation, and demonstrated for the first time the ability of weakly supervised instance segmentation using only keyword annotations.
Ranked #4 on
Image-level Supervised Instance Segmentation
on COCO test-dev
(using extra training data)
Deep Portrait Image Completion and Extrapolation
We evaluate our method on public portrait image datasets, and show that it outperforms other state-of-art general image completion methods.
Graphics
LineNet: a Zoomable CNN for Crowdsourced High Definition Maps Modeling in Urban Environments
Combining LineNet and TTLane, we proposed a pipeline to model HD maps with crowdsourced data for the first time.
Pose2Seg: Detection Free Human Instance Segmentation
We demonstrate that our pose-based framework can achieve better accuracy than the state-of-art detection-based approach on the human instance segmentation problem, and can moreover better handle occlusion.
Ranked #1 on
Human Instance Segmentation
on OCHuman
Deep Online Video Stabilization
In this paper, we solve the video stabilization problem using a convolutional neural network (ConvNet).
Graphics
S4Net: Single Stage Salient-Instance Segmentation
Taking into account the category-independent property of each target, we design a single stage salient instance segmentation framework, with a novel segmentation branch.
A Comparative Study of Algorithms for Realtime Panoramic Video Blending
In this paper, we investigate 6 popular blending algorithms---feather blending, multi-band blending, modified Poisson blending, mean value coordinate blending, multi-spline blending and convolution pyramid blending.
Appearance Harmonization for Single Image Shadow Removal
In this work we propose a fully automatic shadow region harmonization approach that improves the appearance compatibility of the de-shadowed region as typically produced by previous methods.
Sketch2Photo: Internet Image Montage
The composed picture is generated by seamlessly stitching several photographs in agreement with the sketch and text labels; these are found by searching the Internet.
