OOIR: Observatory of International Research

Papers

(The TQCC of Computational Visual Media is 7. The table below lists those papers that are above that threshold based on CrossRef citation counts [max. 250 papers]. The publications cover those that have been published in the past four years, i.e., from 2021-08-01 to 2025-08-01.)

Article	Citations
Heuristic weakly supervised 3D human pose estimation	1629
Geometry-aware 3D pose transfer using transformer autoencoder	1406
Towards harmonized regional style transfer and manipulation for facial images	540
MA2Net: Multi-Scale Adaptive Mixed Attention Network for Image Demoiréing	102
Front Cover	60
3D Indoor Scene Geometry Estimation from a Single Omnidirectional Image: A Comprehensive Survey	56
3D face recognition: A comprehensive survey in 2022	54
Improved fuzzy clustering for image segmentation based on a low-rank prior	43
Controllable multi-domain semantic artwork synthesis	37
A Biophysical-Based Skin Model for Heterogeneous Volume Rendering	35
Neighborhood co-occurrence modeling in 3D point cloud segmentation	29
Recent advances in glinty appearance rendering	27
FRNeRF: Fusion and regularization fields for dynamic view synthesis	27
Temporal vectorized visibility for direct illumination of animated models	23
A causal convolutional neural network for multi-subject motion modeling and generation	23
Front cover	21
Practical construction of globally injective parameterizations with positional constraints	21
Multi-granularity sequence generation for hierarchical image classification	20
Image-guided color mapping for categorical data visualization	20
Anchor-Regularized GAN Priors	20
Central similarity consistency hashing for asymmetric image retrieval	20
HDR-Net-Fusion: Real-time 3D dynamic scene reconstruction with a hierarchical deep reinforcement network	19
Towards robustness and generalization of point cloud representation: A geometry coding method and a large-scale object-level dataset	19
Real-time distance field acceleration based free-viewpoint video synthesis for large sports fields	18
MusicFace: Music-driven expressive singing face synthesis	16

IIDM: Image-to-Image Diffusion Model for Semantic Image Synthesis	16
D2ANet: Difference-aware attention network for multi-level change detection from satellite imagery	16
A survey of urban visual analytics: Advances and future directions	14
ARM3D: Attention-based relation module for indoor 3D object detection	14
DepthGAN: GAN-based depth generation from semantic layouts	13
Watertight surface reconstruction method for CAD models based on optimal transport	13
Reference-guided structure-aware deep sketch colorization for cartoons	13
Sphere face model: A 3D morphable model with hypersphere manifold latent space using joint 2D/3D training	13
Let's all dance: Enhancing amateur dance motions	13
Multi3D: 3D-aware multimodal image synthesis	13
Constructing self-supporting surfaces with planar quadrilateral elements	12
Global video object segmentation with spatial constraint module	12
Addressing Missing Modality Challenges in MRI Images: A Comprehensive Review	11
Mindstorms in Natural Language-Based Societies of Mind	11
Benchmarking visual SLAM methods in mirror environments	11
Prediction of scene plausibility	11
MDFP-Net: A model-driven deep neural network for Fourier ptychography	11
Co-occurrence based texture synthesis	10
Sem-iNeRF: Camera Pose Refinement by Inverting Neural Radiance Fields with Semantic Feature Consistency	10
Deep unfolding multi-scale regularizer network for image denoising	9
MMRelief: Modeling Multi-Human Relief from a Single Photograph	9
EFECL: Feature encoding enhancement with contrastive learning for indoor 3D object detection	8
Front cover	8
Deep panoramic depth prediction and completion for indoor scenes	8
Deep image synthesis from intuitive user input: A review and perspectives	8
Front cover	8
Exploring Contextual Priors for Real-World Image Super-Resolution	8
FCDFusion: A Fast, Low Color Deviation Method for Fusing Visible and Infrared Image Pairs	7
Dynamic ocean inverse modeling based on differentiable rendering	7
A Voronoi diagram approach for detecting defects in 3D printed fiber-reinforced polymers from microscope images	7
Hybrid Mesh-Neural Representation for 3D Transparent Object Reconstruction	7
Message from the editor-in-chief	7
Front cover	7
SGformer: Boosting transformers for indoor lighting estimation from a single image	7
A two-step surface-based 3D deep learning pipeline for segmentation of intracranial aneurysms	7