Search Results for author:
Found 59 papers, 32 papers with code
XHand: Real-time Expressive Hand Avatar
Hand avatars play a pivotal role in a wide array of digital interfaces, enhancing user immersion and facilitating natural interaction within virtual environments.
Fine-Grained Multi-View Hand Reconstruction Using Inverse Rendering
Reconstructing high-fidelity hand models with intricate textures plays a crucial role in enhancing human-object interaction and advancing real-world applications.
TokenPacker: Efficient Visual Projector for Multimodal LLM
However, the visual tokens are redundant and can be considerably increased when dealing with high-resolution images, impairing the efficiency of MLLMs significantly.
PianoMotion10M: Dataset and Benchmark for Hand Motion Generation in Piano Performance
Although key presses can be directly derived from sheet music, the transitional movements among key presses require more extensive guidance in piano performance.
Label-efficient Semantic Scene Completion with Scribble Annotations
Semantic scene completion aims to infer the 3D geometric structures with semantic classes from camera or LiDAR, which provide essential occupancy information in autonomous driving.
HVOFusion: Incremental Mesh Reconstruction Using Hybrid Voxel Octree
Incremental scene reconstruction is essential to the navigation in robotics.
Not All Voxels Are Equal: Hardness-Aware Semantic Scene Completion with Self-Distillation
Furthermore, the voxels in the boundary region are more challenging to differentiate than those in the interior.
MGMap: Mask-Guided Learning for Online Vectorized HD Map Construction
Currently, high-definition (HD) map construction leans towards a lightweight online generation tendency, which aims to preserve timely and reliable road scene information.
HO-Gaussian: Hybrid Optimization of 3D Gaussian Splatting for Urban Scenes
The rapid growth of 3D Gaussian Splatting (3DGS) has revolutionized neural rendering, enabling real-time production of high-quality renderings.
Offboard Occupancy Refinement with Hybrid Propagation for Autonomous Driving
Vision-based occupancy prediction, also known as 3D Semantic Scene Completion (SSC), presents a significant challenge in computer vision.
Traj-LIO: A Resilient Multi-LiDAR Multi-IMU State Estimator Through Sparse Gaussian Process
Nowadays, sensor suits have been equipped with redundant LiDARs and IMUs to mitigate the risks associated with sensor failure.
Osprey: Pixel Understanding with Visual Instruction Tuning
In this paper, we propose Osprey, a mask-text instruction tuning approach, to extend MLLMs by incorporating fine-grained mask regions into language instruction, aiming at achieving pixel-wise visual understanding.
DGNR: Density-Guided Neural Point Rendering of Large Driving Scenes
Despite the recent success of Neural Radiance Field (NeRF), it is still challenging to render large-scale driving scenes with long trajectories, particularly when the rendering quality and efficiency are in high demand.
Semantic-Preserved Point-based Human Avatar
To enable realistic experience in AR/VR and digital entertainment, we present the first point-based human avatar model that embodies the entirety expressive range of digital humans.
Label-efficient Segmentation via Affinity Propagation
In this work, we formulate the affinity modeling as an affinity propagation process, and propose a local and a global pairwise affinity terms to generate accurate soft pseudo labels.
Moiré Backdoor Attack (MBA): A Novel Trigger for Pedestrian Detectors in the Physical World
Next, we embed these Moiré patterns as a backdoor trigger into digital images and use this dataset to train a backdoored detector.
Traj-LO: In Defense of LiDAR-Only Odometry Using an Effective Continuous-Time Trajectory
Therefore, our proposed Traj-LO approach tries to recover the spatial-temporal consistent movement of LiDAR by tightly coupling the geometric information from LiDAR points and kinematic constraints from trajectory smoothness.
Point2Mask: Point-supervised Panoptic Segmentation via Optimal Transport
Weakly-supervised image segmentation has recently attracted increasing research attentions, aiming to avoid the expensive pixel-wise labeling.
Pyramid Deep Fusion Network for Two-Hand Reconstruction from RGB-D Images
Most of the existing methods extract features from color images to estimate the root-aligned hand meshes, which neglect the crucial depth and scale information in the real world.
FastMESH: Fast Surface Reconstruction by Hexagonal Mesh-based Neural Rendering
Despite the promising results of multi-view reconstruction, the recent neural rendering-based methods, such as implicit surface rendering (IDR) and volume rendering (NeuS), not only incur a heavy computational burden on training but also have the difficulties in disentangling the geometric and appearance.
BundleRecon: Ray Bundle-Based 3D Neural Reconstruction
With the growing popularity of neural rendering, there has been an increasing number of neural implicit multi-view reconstruction methods.
Multi-View Stereo Representation Revisit: Region-Aware MVSNet
Comparing to the conventional deep learning-based multi-view stereo methods, our proposed RA-MVSNet approach obtains more complete reconstruction results by taking advantage of signed distance supervision.
Ranked #5 on
Point Clouds
on Tanks and Temples
LiDAR2Map: In Defense of LiDAR-Based Semantic Map Construction Using Online Camera Distillation
To mitigate the defects caused by lacking semantic cues in LiDAR data, we present an online Camera-to-LiDAR distillation scheme to facilitate the semantic learning from image to point cloud.
Bridging the Emotional Semantic Gap via Multimodal Relevance Estimation
To tackle this problem, we propose a multimodal relevance estimation network to capture the relevant semantics among modalities in multimodal emotions.
Multi-View Stereo Representation Revist: Region-Aware MVSNet
It is essential to the textureless regions and surface boundary that cannot be properly reconstructed. To address this issue, we suggest to take advantage of point-to-surface distance so that the model is able to perceive a wider range of surfaces.
Box2Mask: Box-supervised Instance Segmentation via Level-set Evolution
In contrast to fully supervised methods using pixel-wise mask labels, box-supervised instance segmentation takes advantage of simple box annotations, which has recently attracted increasing research attention.
FastHuman: Reconstructing High-Quality Clothed Human in Minutes
We propose an approach for optimizing high-quality clothed human body shapes in minutes, using multi-view posed images.
Box-supervised Instance Segmentation with Level Set Evolution
A simple mask supervised SOLOv2 model is adapted to predict the instance-aware mask map as the level set for each instance.
Improving Nighttime Driving-Scene Segmentation via Dual Image-adaptive Learnable Filters
With DIAL-Filters, we design both unsupervised and supervised frameworks for nighttime driving-scene segmentation, which can be trained in an end-to-end manner.
Warped Convolutional Networks: Bridge Homography to sl(3) algebra by Group Convolution
In this paper, we propose Warped Convolution Networks (WCN) to effectively learn and represent the homography by SL(3) group and sl(3) algebra with group convolution.
ECTLO: Effective Continuous-time Odometry Using Range Image for LiDAR with Small FoV
Prism-based LiDARs are more compact and cheaper than the conventional mechanical multi-line spinning LiDARs, which have become increasingly popular in robotics, recently.
Multiview Textured Mesh Recovery by Differentiable Rendering
Although having achieved the promising results on shape and color recovery through self-supervision, the multi-layer perceptrons-based methods usually suffer from heavy computational cost on learning the deep implicit surface representation.
READ: Large-Scale Neural Scene Rendering for Autonomous Driving
In this paper, a large-scale neural rendering method is proposed to synthesize the autonomous driving scene~(READ), which makes it possible to synthesize large-scale driving scenarios on a PC through a variety of sampling schemes.
Ranked #1 on
Novel View Synthesis
on KITTI
End-to-end Weakly-supervised Single-stage Multiple 3D Hand Mesh Reconstruction from a Single RGB Image
In this paper, we consider the challenging task of simultaneously locating and recovering multiple hands from a single 2D image.
Meta-RangeSeg: LiDAR Sequence Semantic Segmentation Using Multiple Feature Aggregation
LiDAR sensor is essential to the perception system in autonomous vehicles and intelligent robots.
Ranked #18 on
3D Semantic Segmentation
on SemanticKITTI
Image-Adaptive YOLO for Object Detection in Adverse Weather Conditions
Though deep learning-based object detection methods have achieved promising results on the conventional datasets, it is still challenging to locate objects from the low-quality images captured in adverse weather conditions.
Homography Decomposition Networks for Planar Object Tracking
Planar object tracking plays an important role in AI applications, such as robotics, visual servoing, and visual SLAM.
Deep Level Set for Box-supervised Instance Segmentation in Aerial Images
Instead of learning the pairwise affinity, the level set method with the carefully designed energy functions treats the object segmentation as curve evolution, which is able to accurately recover the object's boundaries and prevent the interference from the indistinguishable background and similar objects.
Structure First Detail Next: Image Inpainting with Pyramid Generator
Recent deep generative models have achieved promising performance in image inpainting.
Topology-Preserved Human Reconstruction with Details
It is challenging to directly estimate the human geometry from a single image due to the high diversity and complexity of body shapes with the various clothing styles.
Translational Symmetry-Aware Facade Parsing for 3D Building Reconstruction
Although enjoying the merits of promising results on the semantic parsing, deep learning methods cannot directly make use of the architectural rules, which play an important role for man-made structures.
Oriented RepPoints for Aerial Object Detection
In contrast to the generic object, aerial targets are often non-axis aligned with arbitrary orientations having the cluttered surroundings.
Ranked #7 on
Oriented Object Detection
on DOTA 1.0
Efficient LiDAR Odometry for Autonomous Driving
LiDAR odometry plays an important role in self-localization and mapping for autonomous navigation, which is usually treated as a scan registration problem.
Horizontal-to-Vertical Video Conversion
Alongside the prevalence of mobile videos, the general public leans towards consuming vertical videos on hand-held devices.
Weakly-Supervised Multi-Face 3D Reconstruction
3D face reconstruction plays a very important role in many real-world multimedia applications, including digital entertainment, social media, affection analysis, and person identification.
DeVLBert: Learning Deconfounded Visio-Linguistic Representations
In this paper, we propose to investigate the problem of out-of-domain visio-linguistic pretraining, where the pretraining data distribution differs from that of downstream data on which the pretrained model will be fine-tuned.
Deep Time-Stream Framework for Click-Through Rate Prediction by Tracking Interest Evolution
Click-through rate (CTR) prediction is an essential task in industrial applications such as video recommendation.
Attribute-aware Pedestrian Detection in a Crowd
To tackle this critical problem, we propose an attribute-aware pedestrian detector to explicitly model people's semantic attributes in a high-level feature detection fashion.
SuPer: A Surgical Perception Framework for Endoscopic Tissue Manipulation with Surgical Robotics
In this work, we propose a novel surgical perception framework, SuPer, for surgical robotic control.
Manifold Adversarial Learning
All the existing adversarial training methods consider only how the worst perturbed examples (i. e., adversarial examples) could affect the model output.
Single-Shot Bidirectional Pyramid Networks for High-Quality Object Detection
Recent years have witnessed many exciting achievements for object detection using deep learning techniques.
Robust Estimation of Similarity Transformation for Visual Object Tracking
In order to efficiently search in such a large 4-DoF space in real-time, we formulate the problem into two 2-DoF sub-problems and apply an efficient Block Coordinates Descent solver to optimize the estimation result.
Feature Agglomeration Networks for Single Stage Face Detection
In this paper, we propose a novel simple yet effective framework of "Feature Agglomeration Networks" (FANet) to build a new single stage face detector, which not only achieves state-of-the-art performance but also runs efficiently.
Two Birds with One Stone: Transforming and Generating Facial Images with Iterative GAN
Generating high fidelity identity-preserving faces with different facial attributes has a wide range of applications.
Scalable Image Retrieval by Sparse Product Quantization
Unlike the existing approaches, in this paper, we propose a novel approach called Sparse Product Quantization (SPQ) to encoding the high-dimensional feature vectors into sparse representation.
Reliable Patch Trackers: Robust Visual Tracking by Exploiting Reliable Patches
Most modern trackers typically employ a bounding box given in the first frame to track visual objects, where their tracking results are often sensitive to the initialization.
Learning Bregman Distance Functions and Its Application for Semi-Supervised Clustering
Learning distance functions with side information plays a key role in many machine learning and data mining applications.
Adaptive Regularization for Transductive Support Vector Machine
In this framework, SVM and TSVM can be regarded as a learning machine without regularization and one with full regularization from the unlabeled data, respectively.
Efficient Convex Relaxation for Transductive Support Vector Machine
We consider the problem of Support Vector Machine transduction, which involves a combinatorial problem with exponential computational complexity in the number of unlabeled examples.
