Kun Wang

papers

728

total citations

papers (25)

RigNet: Repetitive Image Guided Network for Depth Completion

ECCV 2022arXiv

154

citations

Regularizing Nighttime Weirdness: Efficient Self-Supervised Monocular Depth Estimation in the Dark

ICCV 2021arXiv

102

citations

Kill Two Birds with One Stone: Rethinking Data Augmentation for Deep Long-tailed Learning

ICLR 2024

citations

Completion as Enhancement: A Degradation-Aware Selective Image Guided Network for Depth Completion

CVPR 2025arXiv

citations

Siamese DETR

CVPR 2023arXiv

citations

Depth-Centric Dehazing and Depth-Estimation from Real-World Hazy Driving Video

AAAI 2025arXiv

citations

Auditing Meta-Cognitive Hallucinations in Reasoning Large Language Models

NEURIPS 2025arXiv

citations

X-Learner: Learning Cross Sources and Tasks for Universal Visual Representation

ECCV 2022arXiv

citations

AltNeRF: Learning Robust Neural Radiance Field via Alternating Depth-Pose Optimization

AAAI 2024arXiv

citations

Breaking the Discretization Barrier of Continuous Physics Simulation Learning

NEURIPS 2025arXiv

citations

TMT-VIS: Taxonomy-aware Multi-dataset Joint Training for Video Instance Segmentation

NEURIPS 2023arXiv

citations

Unleashing Foundation Vision Models: Adaptive Transfer for Diverse Data-Limited Scientific Domains

NEURIPS 2025arXiv

citations

LST-Net: Learning a Convolutional Neural Network with a Learnable Sparse Transform

ECCV 2020

citations

Exploring Forensic Dental Identification with Deep Learning

NEURIPS 2021

citations

Earthfarsser: Versatile Spatio-Temporal Dynamical Systems Modeling in One Model

AAAI 2024

citations

Gradient-based Visual Explanation for Transformer-based CLIP

ICML 2024

citations

Kun Wang

papers (25)

RigNet: Repetitive Image Guided Network for Depth Completion

Regularizing Nighttime Weirdness: Efficient Self-Supervised Monocular Depth Estimation in the Dark

Adapting Object Detectors with Conditional Domain Normalization

Deciphering Spatio-Temporal Graph Forecasting: A Causal Lens and Treatment

GoT: Unleashing Reasoning Capability of MLLM for Visual Generation and Editing

Tri-Perspective View Decomposition for Geometry-Aware Depth Completion

Multi-modal Masked Pre-training for Monocular Panoramic Depth Completion

PUMA: Empowering Unified MLLM with Multi-granular Visual Generation

Driving-Video Dehazing with Non-Aligned Regularization for Safety Assistance

Graph Sparsification via Mixture of Graphs

ViLLa: Video Reasoning Segmentation with Large Language Model

Kill Two Birds with One Stone: Rethinking Data Augmentation for Deep Long-tailed Learning

Completion as Enhancement: A Degradation-Aware Selective Image Guided Network for Depth Completion

Siamese DETR

Depth-Centric Dehazing and Depth-Estimation from Real-World Hazy Driving Video

Auditing Meta-Cognitive Hallucinations in Reasoning Large Language Models

X-Learner: Learning Cross Sources and Tasks for Universal Visual Representation

AltNeRF: Learning Robust Neural Radiance Field via Alternating Depth-Pose Optimization

Breaking the Discretization Barrier of Continuous Physics Simulation Learning

TMT-VIS: Taxonomy-aware Multi-dataset Joint Training for Video Instance Segmentation

Unleashing Foundation Vision Models: Adaptive Transfer for Diverse Data-Limited Scientific Domains

LST-Net: Learning a Convolutional Neural Network with a Learnable Sparse Transform

Exploring Forensic Dental Identification with Deep Learning

Earthfarsser: Versatile Spatio-Temporal Dynamical Systems Modeling in One Model

Gradient-based Visual Explanation for Transformer-based CLIP

papers (25)

RigNet: Repetitive Image Guided Network for Depth Completion

Regularizing Nighttime Weirdness: Efficient Self-Supervised Monocular Depth Estimation in the Dark

Adapting Object Detectors with Conditional Domain Normalization

Deciphering Spatio-Temporal Graph Forecasting: A Causal Lens and Treatment

GoT: Unleashing Reasoning Capability of MLLM for Visual Generation and Editing

Tri-Perspective View Decomposition for Geometry-Aware Depth Completion

Multi-modal Masked Pre-training for Monocular Panoramic Depth Completion

PUMA: Empowering Unified MLLM with Multi-granular Visual Generation

Driving-Video Dehazing with Non-Aligned Regularization for Safety Assistance

Graph Sparsification via Mixture of Graphs

ViLLa: Video Reasoning Segmentation with Large Language Model

Kill Two Birds with One Stone: Rethinking Data Augmentation for Deep Long-tailed Learning

Completion as Enhancement: A Degradation-Aware Selective Image Guided Network for Depth Completion

Siamese DETR

Depth-Centric Dehazing and Depth-Estimation from Real-World Hazy Driving Video

Auditing Meta-Cognitive Hallucinations in Reasoning Large Language Models

X-Learner: Learning Cross Sources and Tasks for Universal Visual Representation

AltNeRF: Learning Robust Neural Radiance Field via Alternating Depth-Pose Optimization

Breaking the Discretization Barrier of Continuous Physics Simulation Learning

TMT-VIS: Taxonomy-aware Multi-dataset Joint Training for Video Instance Segmentation

Unleashing Foundation Vision Models: Adaptive Transfer for Diverse Data-Limited Scientific Domains

LST-Net: Learning a Convolutional Neural Network with a Learnable Sparse Transform

Exploring Forensic Dental Identification with Deep Learning

Earthfarsser: Versatile Spatio-Temporal Dynamical Systems Modeling in One Model

Gradient-based Visual Explanation for Transformer-based CLIP