Is this you? Claim this profile to correct it, add a bio and choose the work people see first.
Claim this profileWorks84 from public data
- RoboMIND: Benchmark on Multi-embodiment Intelligence Normative Data for Robot Manipulation244
This paper introduces RoboMIND (Multi-embodiment Intelligence Normative Data for Robot Manipulation), a dataset containing 107k demonstration trajectories across 479 diverse tasks involving 96 object classes, the largest multi-embodiment teleoperation dataset collected on a unified platform.
- Perceiving and Modeling Density for Image Dehazing156
A novel Separable Hybrid Attention (SHA) module is proposed to perceive haze density by capturing positional-sensitive features in the orthogonal directions to achieve this goal and a density encoding matrix is proposed to model the uneven distribution of the haze explicitly.
- NightHazeFormer: Single Nighttime Haze Removal Using Prior Query Transformer143
Extensive experiments on several synthetic and real-world datasets demonstrate the superiority of the NightHazeFormer over state-of-the-art nighttime haze removal methods in terms of both visually and quantitatively.
- 95
- Sparse Sampling Transformer with Uncertainty-Driven Ranking for Unified Removal of Raindrops and Rain Streaks89
This paper proposes a Sparse Sampling Transformer based on Uncertainty-Driven Ranking, dubbed UDR-S2Former, which can adaptively sample relevant image degradation information to model underlying degradation relationships and clearly outperforms state-of-the-art methods for all benchmarks.
- MSP-Former: Multi-Scale Projection Transformer for Single Image Desnowing88
A multi-scale projection transformer (MSP-Former), which understands and covers a variety of snow degradation features in a multi-path manner, and integrates comprehensive scene context information for clean reconstruction via self-attention operation, achieves the SOTA performance on three desnowing benchmark datasets while costing the low parameters and computational complexity.
- NTIRE 2024 Challenge on Low Light Image Enhancement: Methods and Results85
This paper meticulously evaluates the state-of-the-art advancements in enhancing low-light images, reflecting the significant progress and creativity in this field.
- Five A$^{+}$ Network: You Only Need 9K Parameters for Underwater Image Enhancement68
Thorough extensive experiments and comprehensive visual comparison, it is shown that FA$^{+}$Net outperforms previous approaches by obtaining state-of-the-art performance on multiple datasets while significantly reducing both parameter count and computational complexity.
- Underwater Light Field Retention : Neural Rendering for Underwater Imaging68
UWNR is a data-driven neural network that implicitly learns the natural degenerated model from authentic underwater images, avoiding introducing erroneous biases by hand-craft imaging models and is able to synthesize a wide variety of underwater images from one clean image with various realistic underwater images.
- Lift3D Foundation Policy: Lifting 2D Large-Scale Pretrained Models for Robust 3D Robotic Manipulation61
The Lift3D framework is proposed, which progressively enhances 2D foundation models with implicit and explicit 3D robotic representations to construct a robust 3D manipulation policy and consistently outperforms previous state-of-the-art methods across several simulation benchmarks and real-world scenarios.
- JarvisIR: Elevating Autonomous Driving Perception with Intelligent Image Restoration55
JarvisIR, a VLM-powered agent that leverages the VLM as a controller to manage multiple expert restoration models to enhance system robustness, reduce hallucinations, and improve generalizability in real-world adverse weather, is proposed.
- SnowFormer: Context Interaction Transformer with Scale-awareness for Single Image Desnowing55
A powerful architecture dubbed as SnowFormer performs Scale-aware Feature Aggregation in the encoder to capture rich snow information of various degradations and uses a novel Context Interaction Trans-former Block in the decoder in order to tackle with large-scale degradation.
- Roles of Identified Long Noncoding RNA in Diabetic Nephropathy52
Recent studies reported that the progression of DN is closely related to the expression of long noncoding RNA (lncRNA), which is important for the early diagnosis and targeted intervention of DN.
- 42
- SegDINO: An Efficient Design for Medical and Natural Image Segmentation with DINO-V340
SegDINO is an efficient segmentation framework that couples a frozen DINOv3 backbone with a lightweight decoder, and utilizes a lightweight MLP head to directly predict segmentation masks, which minimizes trainable parameters while preserving the representational power of foundation features.
- NTIRE 2025 Challenge on Day and Night Raindrop Removal for Dual-Focused Images: Methods and Results37
This paper reviews the NTIRE 2025 Challenge on Day and Night Raindrop Removal for Dual-Focused Images to establish a new and powerful benchmark for the task of removing raindrops under varying lighting and focus conditions.
- Jieduquyuziyin Prescription Suppresses Inflammatory Activity of MRL/lpr Mice and Their Bone Marrow-Derived Macrophages via Inhibiting Expression of IRAK1-NF-κB Signaling Pathway32
It is demonstrated that JP could inhibit the inflammatory activity of MRL/lpr mice and their BMDMs by suppressing the activation of IRAK1-NF-κB signaling and was supposed to be a good choice for the treatment of SLE.
- An Empirical Study of GPT-4o Image Generation Capabilities31
An empirical study of GPT-4o's image generation capabilities is conducted, benchmarking it against leading open-source and commercial models and identifying promising directions for future unified generative models, emphasizing the role of architectural design and data scaling.
- 31
- FastDriveVLA: Efficient End-to-End Driving via Plug-and-Play Reconstruction-based Token Pruning29
FastDriveVLA is proposed, a novel reconstruction-based vision token pruning framework designed specifically for autonomous driving that includes a plug-and-play visual token pruner called ReconPruner, which prioritizes foreground information through MAE-style pixel reconstruction.
- 27
- 26
- 24
- 24
- 21
Publication data from OpenAlex, with missing venues and authors filled in from Crossref; citation counts are the higher of OpenAlex and Semantic Scholar, last synced 2026-10-12. One-sentence summaries under some papers are written by Semantic Scholar’s model. Citation counts may be lower than on Google Scholar, which indexes more sources.
Report an error
Wrong papers, two people merged into one, or a profile that should not be here? Tell us and we will fix or hide it.