Kui Jia

48

Papers

45

Total Citations

Papers (48)

ComboVerse: Compositional 3D Assets Creation Using Spatially-Aware Diffusion Guidance

Multi-StyleGS: Stylized Gaussian Splatting with Multiple Styles

Towards Real-World Test-Time Adaptation: Tri-net Self-Training with Balanced Normalization

GS-IR: 3D Gaussian Splatting for Inverse Rendering

Improving the Generalization of Segmentation Foundation Model under Distribution Shift via Weakly Supervised Adaptation

SAM-6D: Segment Anything Model Meets Zero-Shot 6D Object Pose Estimation

Towards Understanding Cross and Self-Attention in Stable Diffusion for Text-Guided Image Editing

Improving Training of Deep Neural Networks via Singular Value Bounding

A Skeleton-Bridged Deep Learning Approach for Generating Meshes of Complex Topologies From Single RGB Images

Domain-Symmetric Networks for Adversarial Domain Adaptation

Unsupervised Domain Adaptation via Structurally Regularized Deep Clustering

MTL-NAS: Task-Agnostic Neural Architecture Search Towards General-Purpose Multi-Task Learning

3D AffordanceNet: A Benchmark for Visual Object Affordance Understanding

Learning Parallel Dense Correspondence From Spatio-Temporal Descriptors for Efficient and Robust 4D Reconstruction

Sign-Agnostic Implicit Learning of Surface Self-Similarities for Shape Modeling and Reconstruction From Raw Point Clouds

Deep Optimized Priors for 3D Shape Modeling and Reconstruction

Exact Feature Distribution Matching for Arbitrary Style Transfer and Domain Generalization

VISTA: Boosting 3D Object Detection via Dual Cross-VIew SpaTial Attention

Towards Discovering the Effectiveness of Moderately Confident Samples for Semi-Supervised Learning

RGBD2: Generative Scene Synthesis via Incremental View Inpainting Using RGBD Diffusion Models

A New Benchmark: On the Utility of Synthetic Data With Blender for Bare Supervised Learning and Downstream Domain Adaptation

HelixSurf: A Robust and Efficient Neural Implicit Surface Learning of Indoor Scenes With Iterative Intertwined Regularization

Human Action Recognition Using Factorized Spatio-Temporal Convolutional Networks

Lattice Long Short-Term Memory for Human Action Recognition

A Joint Intrinsic-Extrinsic Prior Model for Retinex

HEMlets Pose: Learning Part-Centric Heatmap Triplets for Accurate 3D Human Pose Estimation

PARN: Position-Aware Relation Networks for Few-Shot Learning

Deep Mesh Reconstruction From Single RGB Images via Topology Modification Networks

Instance Segmentation in 3D Scenes Using Semantic Superpoint Tree Networks

DualPoseNet: Category-Level 6D Object Pose and Size Estimation Using Dual Pose Network With Refined Learning of Pose Consistency

SA-ConvONet: Sign-Agnostic Optimization of Convolutional Occupancy Networks

Perception-Aware Multi-Sensor Fusion for 3D LiDAR Semantic Segmentation

Geometry-Aware Self-Training for Unsupervised Domain Adaptation on Object Point Clouds

On the Robustness of Open-World Test-Time Training: Self-Training with Dynamic Prototype Expansion

Prof. Robot: Differentiable Robot Rendering Without Static and Self-Collisions

Fantasia3D: Disentangling Geometry and Appearance for High-quality Text-to-3D Content Creation

Label Propagation with Augmented Anchors: A Simple Semi-Supervised Learning baseline for Unsupervised Domain Adaptation

Object as Hotspots: An Anchor-Free 3D Object Detection Approach via Firing of Hotspots

Category-Level 6D Object Pose and Size Estimation Using Self-Supervised Deep Prior Deformation Networks

DCL-Net: Deep Correspondence Learning Network for 6D Pose Estimation

Stochastic Consensus: Enhancing Semi-Supervised Learning with Consistency of Stochastic Classifiers

Quasi-Balanced Self-Training on Noise-Aware Synthesis of Object Point Clouds for Closing Domain Gap

VI-Net: Boosting Category-level 6D Object Pose Estimation via Learning Decoupled Rotations on the Spherical Representations

Multi-marginal Wasserstein GAN

Grasp Proposal Networks: An End-to-End Solution for Visual Learning of Robotic Grasps

Sparse Steerable Convolutions: An Efficient Learning of SE(3)-Equivariant Features for Estimation and Tracking of Object Poses in 3D Space

Revisiting Realistic Test-Time Training: Sequential Inference and Adaptation by Anchored Clustering

TANGO: Text-driven Photorealistic and Robust 3D Stylization via Lighting Decomposition