Guosheng Lin

73

Papers

469

Total Citations

Papers (73)

GaussianEditor: Swift and Controllable 3D Editing with Gaussian Splatting

MeshAnything V2: Artist-Created Mesh Generation with Adjacent Mesh Tokenization

REACTO: Reconstructing Articulated Objects from a Single Video

MagicArticulate: Make Your 3D Models Articulation-Ready

CADCrafter: Generating Computer-Aided Design Models from Unconstrained Images

Semi-supervised Class-Agnostic Motion Prediction with Pseudo Label Regeneration and BEVMix

ADHMR: Aligning Diffusion-based Human Mesh Recovery via Direct Preference Optimization

Fine Structure-Aware Sampling: A New Sampling Training Scheme for Pixel-Aligned Implicit Models in Single-View Human Reconstruction

IPVTON: Image-based 3D Virtual Try-on with Image Prompt Adapter

Self-Supervised Class-Agnostic Motion Prediction with Spatial and Temporal Consistency Regularizations

R-Cyclic Diffuser: Reductive and Cyclic Latent Diffusion for 3D Clothed Human Digitalization

Sculpt3D: Multi-View Consistent Text-to-3D Generation with Sparse 3D Prior

Deep Convolutional Neural Fields for Depth Estimation From a Single Image

Efficient Piecewise Training of Deep Structured Models for Semantic Segmentation

Fast Training of Triplet-Based Deep Binary Embedding Networks

Sequential Person Recognition in Photo Albums With a Recurrent Network

RefineNet: Multi-Path Refinement Networks for High-Resolution Semantic Segmentation

MoNet: Deep Motion Exploitation for Video Object Segmentation

Bootstrapping the Performance of Webly Supervised Semantic Segmentation

Learning Markov Clustering Networks for Scene Text Detection

CANet: Class-Agnostic Segmentation Networks With Iterative Refinement and Attentive Few-Shot Learning

Towards Robust Curve Text Detection With Conditional Spatial Expansion

SpSequenceNet: Semantic Segmentation Network on 4D Point Clouds

Multi-Path Region Mining for Weakly Supervised 3D Semantic Segmentation on Point Clouds

CRNet: Cross-Reference Networks for Few-Shot Segmentation

Cross-Domain Semantic Segmentation via Domain-Invariant Interactive Relation Transfer

DeepEMD: Few-Shot Image Classification With Differentiable Earth Mover's Distance and Structured Classifiers

Exploring Bottom-Up and Top-Down Cues With Attentive Learning for Webly Supervised Object Detection

Self-Point-Flow: Self-Supervised Scene Flow Estimation From Point Clouds With Optimal Transport and Random Walk

Few-Shot Incremental Learning With Continually Evolved Classifiers

Progressive Modality Reinforcement for Human Multimodal Emotion Recognition From Unaligned Multimodal Sequences

CT-Net: Complementary Transfering Network for Garment Transfer With Arbitrary Geometric Changes

HCRF-Flow: Scene Flow From Point Clouds With Continuous High-Order CRFs and Position-Aware Flow Embedding

RigidFlow: Self-Supervised Scene Flow Learning on Point Clouds by Local Rigidity Prior

Weakly Supervised Segmentation on Outdoor 4D Point Clouds With Temporal Matching and Spatial Graph Propagation

Expanding Large Pre-Trained Unimodal Models With Multimodal Information Injection for Image-Text Multimodal Classification

3D Cinemagraphy From a Single Image

Weakly Supervised Class-Agnostic Motion Prediction for Autonomous Driving

Neural Vector Fields: Implicit Representation by Explicit Learning

TAPS3D: Text-Guided 3D Textured Shape Generation From Pseudo Supervision

Pyramid Graph Networks With Connection Attentions for Region-Based One-Shot Semantic Segmentation

SegEQA: Video Segmentation Based Visual Attention for Embodied Question Answering

Self-Supervised 3D Skeleton Action Representation Learning With Motion Consistency and Continuity

Context Decoupling Augmentation for Weakly Supervised Semantic Segmentation

Learning Meta-Class Memory for Few-Shot Semantic Segmentation

Meta Navigator: Search for a Good Adaptation Policy for Few-Shot Learning

Neural Video Depth Stabilizer

Label-Guided Knowledge Distillation for Continual Semantic Segmentation on 2D Images and 3D Point Clouds

Self-Calibrated Cross Attention Network for Few-Shot Segmentation

Collaborative Propagation on Multiple Instance Graphs for 3D Instance Segmentation with Single-point Supervision

Human Interaction Learning on 3D Skeleton Point Clouds for Video Violence Recognition

Graph Edit Distance Reward: Learning to Edit Scene Graph

TRRNet: Tiered Relation Reasoning for Compositional Visual Question Answering

Splitting vs. Merging: Mining Object Regions with Discrepancy and Intersection Loss for Weakly Supervised Semantic Segmentation

Structure-Aware Generation Network for Recipe Generation from Images

IntegratedPIFu: Integrated Pixel Aligned Implicit Function for Single-View Human Reconstruction

General Object Pose Transformation Network from Unpaired Data

Dynamically Transformed Instance Normalization Network for Generalizable Person Re-identification

Learning Regional Purity for Instance Segmentation on 3D Point Clouds

Dual Adaptive Transformations for Weakly Supervised Point Cloud Segmentation

Deeply Learning the Messages in Message Passing Inference

NeurIPS 2015arXiv

Attention Is Not Enough: Mitigating the Distribution Discrepancy in Asynchronous Multimodal Sequence Fusion

TacoDepth: Towards Efficient Radar-Camera Depth Estimation with One-stage Fusion

Attribute-formed Class-specific Concept Space: Endowing Language Bottleneck Model with Better Interpretability and Scalability

SurfaceSplat: Connecting Surface Reconstruction and Gaussian Splatting

Towards Effective Foundation Model Adaptation for Extreme Cross-Domain Few-Shot Learning

MotionAgent: Fine-grained Controllable Video Generation via Motion Field Agent

IT3D: Improved Text-to-3D Generation with Explicit View Synthesis

S-DyRF: Reference-Based Stylized Radiance Fields for Dynamic Scenes

AttriHuman-3D: Editable 3D Human Avatar Generation with Attribute Decomposition and Indexing

3D Pose Transfer with Correspondence Learning and Mesh Refinement

S-PIFu: Integrating Parametric Human Models with PIFu for Single-view Clothed Human Reconstruction

Toward Re-Identifying Any Animal