Search Results for author:
Found 25 papers, 11 papers with code
TSdetector: Temporal-Spatial Self-correction Collaborative Learning for Colonoscopy Video Detection
CNN-based object detection models that strike a balance between performance and speed have been gradually used in polyp detection tasks.
Closely Interactive Human Reconstruction with Proxemics and Physics-Guided Adaption
Specifically, we first design a latent representation based on Vector Quantised-Variational AutoEncoder (VQ-VAE) to model human interaction.
Knowledge NeRF: Few-shot Novel View Synthesis for Dynamic Articulated Objects
To clearly reconstruct dynamic scenes, we propose a new framework by considering two frames at a time. We pretrain a NeRF model for an articulated object. When articulated objects moves, Knowledge NeRF learns to generate novel views at the new state by incorporating past knowledge in the pretrained NeRF model with minimal observations in the present state.
MatChat: A Large Language Model and Application Service Platform for Materials Science
The prediction of chemical synthesis pathways plays a pivotal role in materials science research.
CrowdRec: 3D Crowd Reconstruction from Single Color Images
To promote a more reasonable spatial distribution, we further propose a crowd constraint to refine the single-person network parameters.
Reconstructing Groups of People with Hypergraph Relational Reasoning
To address the obstacles, we fully exploit crowd features for reconstructing groups of people from a monocular image.
Reconstructing Interacting Hands with Interaction Prior from Monocular Images
Our key idea is to first construct a two-hand interaction prior and recast the interaction reconstruction task as the conditional sampling from the prior.
4D Myocardium Reconstruction with Decoupled Motion and Shape Model
Estimating the shape and motion state of the myocardium is essential in diagnosing cardiovascular diseases. However, cine magnetic resonance (CMR) imaging is dominated by 2D slices, whose large slice spacing challenges inter-slice shape reconstruction and motion acquisition. To address this problem, we propose a 4D reconstruction method that decouples motion and shape, which can predict the inter-/intra- shape and motion estimation from a given sparse point cloud sequence obtained from limited slices.
Nonrigid Object Contact Estimation With Regional Unwrapping Transformer
Based on this representation, our Regional Unwrapping Transformer (RUFormer) learns the correlation priors across regions from monocular inputs and predicts corresponding contact and deformed transformations.
Physics-Guided Human Motion Capture with Pose Probability Modeling
To address the obstacles, our key-idea is to employ physics as denoising guidance in the reverse diffusion process to reconstruct physically plausible human motion from a modeled pose probability distribution.
Synthesizing Physically Plausible Human Motions in 3D Scenes
Experimental results demonstrate that our framework can synthesize physically plausible long-term human motions in complex 3D scenes.
Semi-supervised Hand Appearance Recovery via Structure Disentanglement and Dual Adversarial Discrimination
The core of our approach is to first disentangle the bare hand structure from those degraded images and then wrap the appearance to this structure with a dual adversarial discrimination (DAD) scheme.
HMDO: Markerless Multi-view Hand Manipulation Capture with Deformable Objects
We construct the first markerless deformable interaction dataset recording interactive motions of the hands and deformable objects, called HMDO (Hand Manipulation with Deformable Objects).
xTrimoABFold: De novo Antibody Structure Prediction without MSA
Its improvement in both accuracy and efficiency makes it a valuable tool for de novo antibody design and could make further improvements in immuno-theory.
Occluded Human Body Capture with Self-Supervised Spatial-Temporal Motion Prior
To address the obstacles, our key-idea is to employ non-occluded human data to learn a joint-level spatial-temporal motion prior for occluded human with a self-supervised strategy.
Ranked #2 on
Unsupervised 3D Human Pose Estimation
on Human3.6M
3D Human Pose Estimation
Unsupervised 3D Human Pose Estimation
3D Face Parsing via Surface Parameterization and 2D Semantic Segmentation Network
The topological disk-like 2D face image containing spatial and textural information is transformed from the sampled 3D face data through the face parameterization algorithm, and a specific 2D network called CPFNet is proposed to achieve the semantic segmentation of the 2D parameterized face data with multi-scale technologies and feature aggregation.
Stability-driven Contact Reconstruction From Monocular Color Images
Our key idea is to reconstruct the contact pattern directly from monocular images, and then utilize the physical stability criterion in the simulation to optimize it.
Neural MoCon: Neural Motion Control for Physically Plausible Human Motion Capture
Our key-idea is to use real physical supervisions to train a target pose distribution prior for sampling-based motion control to capture physically plausible human motion.
DeepSSN: a deep convolutional neural network to assess spatial scene similarity
Spatial-query-by-sketch is an intuitive tool to explore human spatial knowledge about geographic environments and to support communication with scene database queries.
Dynamic Multi-Person Mesh Recovery From Uncalibrated Multi-View Cameras
Dynamic multi-person mesh recovery has been a hot topic in 3D vision recently.
Interacting Two-Hand 3D Pose and Shape Reconstruction From Single Color Image
In this paper, we propose a novel deep learning framework to reconstruct 3D hand poses and shapes of two interacting hands from a single color image.
Ranked #6 on
3D Interacting Hand Pose Estimation
on InterHand2.6M
TravelNet: Self-Supervised Physically Plausible Hand Motion Learning From Monocular Color Images
In this paper, we embed physical constraints on the per-frame estimated motions in both spatial and temporal space.
DeepCloth: Neural Garment Representation for Shape and Style Editing
In this work, we introduce, DeepCloth, a unified framework for garment representation, reconstruction, animation and editing.
Music2Dance: DanceNet for Music-driven Dance Generation
Synthesize human motions from music, i. e., music to dance, is appealing and attracts lots of research interests in recent years.
Ranked #7 on
Motion Synthesis
on AIST++
Robust Non-Rigid Motion Tracking and Surface Reconstruction Using L0 Regularization
We present a new motion tracking method to robustly reconstruct non-rigid geometries and motions from single view depth inputs captured by a consumer depth sensor.
