Is this you? Claim this profile to correct it, add a bio and choose the work people see first.
Claim this profileWorks59 from public data
- MixFormer: Mixing Features across Windows and Dimensions152
This work combines local-window self-attention with depth-wise convolution in a parallel design, modeling cross-window connections to enlarge the receptive fields and proposes bi-directional interactions across branches to provide complementary clues in the channel and spatial dimensions.
- EfficientNeRF - Efficient Neural Radiance Fields141
This paper presents EfficientNeRF as an efficient NeRF-based method to represent 3D scene and synthesize novel-view images and proposes valid and pivotal sampling at the coarse and fine stage, respectively, to significantly improve sampling efficiency.
- Toward High-Quality HDR Deghosting With Conditional Diffusion Models121
The HDR deghosting problem is formulated as an image generation that leverages LDR features as the diffusion model’s condition, consisting of the feature condition generator and the noise predictor and the noise predictor achieves state-of-the-art performances and well generalization to real-world images.
- Ref-NeuS: Ambiguity-Reduced Neural Implicit Surface Learning for Multi-View Reconstruction with Reflection87
This work utilizes an anomaly detector to estimate an explicit reflection score with the guidance of multiview context to localize reflective surfaces and designs a reflection-aware photometric loss that adaptively reduces ambiguity by modeling rendered color as a Gaussian distribution, with the reflection score representing the variance.
- Human-Object Interaction Detection via Disentangled Transformer87
This work decouple the triplet prediction into human-object pair detection and interaction classification, and presents Disentangled Transformer, where both encoder and decoder are disentangled to facilitate learning of two sub-tasks.
- 82
- NeRFLiX: High-Quality Neural View Synthesis by Learning a Degradation-Driven Inter-viewpoint MiXer44
This work proposes NeRFLiX, a general NeRF-agnostic restorer paradigm by learning a degradation-driven inter-viewpoint mixer that is able to fuse highly related high-quality training images, pushing the performance of cutting-edge NeRF models to entirely new levels and producing highly photo-realistic synthetic views.
- Bracketing Image Restoration and Enhancement with High-Low Frequency Decomposition41
Inspired by the notion that high/low frequency information is applicable to different degradations, HLNet is introduced, a Bracketing Image Restoration and Enhancement method based on high-low frequency decomposition, thus achieving higher-quality image restoration.
- Generating Content for HDR Deghosting from Frequency View40
The Low-Frequency aware Diffusion (LF-Diff) model is proposed, implementing the DMs in a highly compacted latent space and integrating it into a regression-based model to enhance the details of reconstructed images.
- 33
- NTIRE 2025 Challenge on Efficient Burst HDR and Restoration: Datasets, Methods, and Results30
A comprehensive overview of the NTIRE 2025 Efficient Burst HDR and Restoration Challenge is provided, the proposed solutions are compared, and it serves as a valuable reference for researchers and practitioners in efficient burst HDR and restoration.
- Boosting HDR Image Reconstruction via Semantic Knowledge Transfer25
This framework introduces the Semantic Priors Guided Reconstruction Model (SPGRM), which leverages SDR image semantic knowledge to address ill-posed problems in the initial HDR reconstruction results, and leverages a self-distillation mechanism that constrains the color and content information with semantic knowledge, aligning the external outputs between the baseline and SPGRM.
- Research on the perception of the terrain image of the tourism destination based on multimodal user-generated content data23
The results show that tourists' overall perception of Sanya is based mainly on the cognitive image of natural scenery, human resources, and food, and there are differences between textual and visual cognitive images among the perceptual images when multimodal data is under consideration.
- 19
- 18
- Fine-grained vehicle recognition under low light conditions using EfficientNet and image enhancement on LiDAR point cloud data15
This study introduces a novel method for fine-grained vehicle model recognition using LiDAR in low-light conditions and achieves an accuracy of 98.88% in fine-grained vehicle model recognition and an F1-score of 98.86%, showcasing excellent performance.
- 11
- 11
- 11
- 8
- PRM: Photometric Stereo Based Large Reconstruction Model7
A novel photometric stereo based large reconstruction model to reconstruct high-quality meshes with fine-grained details that models specular color more accurately for images with varying materials and illumination than previous neural rendering methods and supports multiple supervisions for geometry optimization.
- FusionNet: Multi-Model Linear Fusion Framework for Low-Light Image Enhancement7
FusionNet is introduced, a novel multi-model linear fusion framework that operates in parallel to effectively capture global and local features across diverse color spaces by incorporating a linear fusion strategy underpinned by Hilbert space theoretical guarantees.
- 7
- Effects of Different Visual Feedback Types on Perception of Online Wait7
The study findings indicate the salience of visual feedback may significantly affect users’ time perception, explicit visual feedback provides users with more perceived control as well as more attention.
- RETRACTED: Pointing Cursor Interaction in Virtual Reality from the Perspective of Distance Perception7
The research discloses the factors affecting the perception of absolute distance, and guides the interaction and stereo pointing design of VR.
- An EfficientNetv2-based method for coal conveyor belt foreign object detection6
A foreign object detection method for coal conveyor belts based on EfficientNetv2 that outperforms some other state-of-the-art (SOTA) models and can effectively complete the detection of foreign objects on coal conveyor belts.
- 5
- HVI-CIDNet+: Beyond Extreme Darkness for Low-Light Image Enhancement4
This work proposes HVI-CIDNet+, a Color and Intensity Decoupling Network designed to restore degraded content and mitigate color distortion in extremely dark regions, and introduces a Region Refinement Block that combines convolution for information-rich regions with attention for information-scarce regions, enabling accurate brightness adjustment.
- Radiomics analysis using machine learning to predict perineural invasion in pancreatic cancer4
A preoperative CECT-based radiomic model integrating clinical and radiomic features exhibited excellent performance in predicting the probability of perineural invasion in patients with pancreatic cancer.
- 4
- Prognostic model identification of ribosome biogenesis-related genes in pancreatic cancer based on multiple machine learning analyses3
The research underscores the critical role of ribosome biogenesis in the progression and treatment resistance of pancreatic cancer, offering valuable new perspectives for prognostic evaluation and therapeutic response prediction in pancreatic cancer.
- Exploring tourist shopping from the perspective of duty-free shopping: An analysis of online reviews3
- 3
- 3
- Research on Prediction model of Carotid‐Femoral Pulse Wave Velocity: Based on Machine Learning Algorithm2
A predictive model based on brachial‐ankle pulse wave velocity and other the accessible clinical parameters is developed based on brachial‐ankle pulse wave velocity and other the accessible clinical parameters.
- 2
- Multi-UAV cooperative task allocation based on IDACLD2
Considering cases involving UAV faults, this study proposes different fault handling strategies to distinguish different fault types and better fit the actual situation of UAV missions.
- 2
- 2
- 1
- Development and Validation of a Centrosome Amplification-Related Prognostic Model in Pancreatic Cancer: Multi-Omics Guided Risk Stratification and Tumor Microenvironment1
This study deciphers the critical role of centrosome amplification in driving pancreatic adenocarcinoma progression and therapy resistance and identifies 23 centrosome amplification-related prognostic genes, with IFI27, KIF20A, KLK10, SPINK7, and TOP2A serving as highly specific diagnostic and prognostic biomarkers.
- 1
- 1
- 1
- 1
- 1
- –
- –
- –
- –
- –
- –
- –
- –
- Adaptive Model Prediction Control-Based Multi-Terrain Trajectory Tracking Framework for Mobile Spherical Robots–
A modified adaptive RBF neural network is proposed to represent all uncertainties in kinodynamics, the Lyapunov function is utilized to design its adaptive law, and a variable step-size algorithm is employed in the weights update procedure to accelerate convergence and improve stability.
- –
- –
- –
- Study on Evidence Reliability Weighting Method Based on Two-tuple Linguistic–
Two-tuple linguistic based on incomplete linguistic information is employed to combine the assessment information from experts and conclude the reliability of the evidence, which allows the linguistic description of assessment information given by experts to better avoid some problems.
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 2026-10-15. 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.