OOIR: Observatory of International Research

Papers

(The median citation count of Computational Visual Media is 2. 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 2022-01-01 to 2026-01-01.)

Article	Citations
Ultra-High Resolution Facial Texture Reconstruction from a Single Image	1892
MA2Net: Multi-Scale Adaptive Mixed Attention Network for Image Demoiréing	1709
Towards harmonized regional style transfer and manipulation for facial images	687
Geometry-aware 3D pose transfer using transformer autoencoder	121
Front Cover	111
3D Indoor Scene Geometry Estimation from a Single Omnidirectional Image: A Comprehensive Survey	72
3D face recognition: A comprehensive survey in 2022	66
Heuristic Weakly Supervised 3D Human Pose Estimation	59
Neighborhood co-occurrence modeling in 3D point cloud segmentation	58
Controllable multi-domain semantic artwork synthesis	55
FRNeRF: Fusion and Regularization Fields for Dynamic View Synthesis	54
A Biophysical-Based Skin Model for Heterogeneous Volume Rendering	52
Front Cover	38
Recent advances in glinty appearance rendering	35
Front cover	33
Anchor-Regularized GAN Priors	32
Practical construction of globally injective parameterizations with positional constraints	30
Multi-granularity sequence generation for hierarchical image classification	27
Towards robustness and generalization of point cloud representation: A geometry coding method and a large-scale object-level dataset	26
Central similarity consistency hashing for asymmetric image retrieval	25
Image-guided color mapping for categorical data visualization	23
Temporal vectorized visibility for direct illumination of animated models	23
A causal convolutional neural network for multi-subject motion modeling and generation	22
D2ANet: Difference-aware attention network for multi-level change detection from satellite imagery	21
Real-time distance field acceleration based free-viewpoint video synthesis for large sports fields	21

ARM3D: Attention-based relation module for indoor 3D object detection	20
MusicFace: Music-driven expressive singing face synthesis	20
Message from Guest Editors of the CVM 2025 Special Issue	19
IIDM: Image-to-Image Diffusion Model for Semantic Image Synthesis	19
Watertight surface reconstruction method for CAD models based on optimal transport	16
DepthGAN: GAN-based depth generation from semantic layouts	16
A survey of urban visual analytics: Advances and future directions	15
NeuS-PIR: Learning Relightable Neural Surface Using Pre-Integrated Rendering	15
Sphere face model: A 3D morphable model with hypersphere manifold latent space using joint 2D/3D training	15
Reference-guided structure-aware deep sketch colorization for cartoons	14
Let's all dance: Enhancing amateur dance motions	14
Sem-iNeRF: Camera Pose Refinement by Inverting Neural Radiance Fields with Semantic Feature Consistency	13
Constructing self-supporting surfaces with planar quadrilateral elements	13
Multi3D: 3D-aware multimodal image synthesis	13
MMRelief: Modeling Multi-Human Relief from a Single Photograph	13
Global video object segmentation with spatial constraint module	12
MDFP-Net: A Model-Driven Deep Neural Network for Fourier Ptychography	12
Uncertainty Aware Multiple View Stereo Network with Accurate Supervision	12
Co-occurrence based texture synthesis	12
Mindstorms in Natural Language-Based Societies of Mind	11
Addressing Missing Modality Challenges in MRI Images: A Comprehensive Review	11
Benchmarking visual SLAM methods in mirror environments	11
Deep unfolding multi-scale regularizer network for image denoising	11
Prediction of Scene Plausibility	11
Front cover	10
Front cover	10
Exploring Contextual Priors for Real-World Image Super-Resolution	10
Deep panoramic depth prediction and completion for indoor scenes	10
A Voronoi diagram approach for detecting defects in 3D printed fiber-reinforced polymers from microscope images	10
EFECL: Feature encoding enhancement with contrastive learning for indoor 3D object detection	10
Continuous Indexed Points for Multivariate Volume Visualization	9
Front cover	9
A two-step surface-based 3D deep learning pipeline for segmentation of intracranial aneurysms	9
Deep image synthesis from intuitive user input: A review and perspectives	9
Contents	8
SGformer: Boosting transformers for indoor lighting estimation from a single image	8
Message from the editor-in-chief	8
Hybrid Mesh-Neural Representation for 3D Transparent Object Reconstruction	8
FCDFusion: A Fast, Low Color Deviation Method for Fusing Visible and Infrared Image Pairs	8
Contents	7
Erroneous pixel prediction for semantic image segmentation	7
Point cloud completion via structured feature maps using a feedback network	7
Front cover	7
Visual perception driven collage synthesis	7
Dynamic ocean inverse modeling based on differentiable rendering	7
PuzzleSorter: Certainty-Aware Visual Restoration of Multiple Cultural Artifacts	7
Immersive analytics meets artificial intelligence: A systematic review	7
A survey on facial image deblurring	6
Towards uniform point distribution in feature-preserving point cloud filtering	6
Message from the editor-in-chief	6

Focusing on your subject: Deep subject-aware image composition recommendation networks	6
Joint specular highlight detection and removal in single images via Unet-Transformer	6
An anisotropic Chebyshev descriptor and its optimization for deformable shape correspondence	6
Non-dominated sorting based multi-page photo collage	6
An efficient algorithm for approximate Voronoi diagram construction on triangulated surfaces	6
A visual modeling method for spatiotemporal and multidimensional features in epidemiological analysis: Applied COVID-19 aggregated datasets	6
FilterGNN: Image feature matching with cascaded outlier filters and linear attention	5
Cross-modal learning using privileged information for long-tailed image classification	5
Message from the editor-in-chief	5
A Simple and Effective Filtering Scheme for Improving Neural Fields	5
Super-resolution reconstruction of single image for latent features	5
PVT v2: Improved baselines with pyramid vision transformer	5
Front cover	5
Revitalizing Image Dehazing in the Real World: A High-Quality Dataset and a Customized Method	5
MagicTalk: Implicit and Explicit Correlation Learning for Diffusion-Based Emotional Talking Face Generation	5
Attention mechanisms in computer vision: A survey	5
Continual few-shot patch-based learning for anime-style colorization	5
Noise4Denoise: Leveraging noise for unsupervised point cloud denoising	4
Front Cover	4
ImVoxelENet: Image to Voxels Epipolar Transformer for Multi-View RGB-Based 3D Object Detection	4
3D corrective nose reconstruction from a single image	4
Learning physically based material and lighting decompositions for face editing	4
Exploring a Hierarchical Cross-Attention Transformer for High-Speed Tracking	4
Autocompletion of repetitive stroking with image guidance	4
NPRportrait 1.0: A three-level benchmark for non-photorealistic rendering of portraits	4
Lossless Intrinsic Image Decomposition via Learning Shading Feature Filtering	4
LucIE: Language-Guided Local Image Editing for Fashion Images	4
JNeRF: An efficient heterogeneous NeRF model zoo based on Jittor	4
SAM-driven MAE pre-training and background-aware meta-learning for unsupervised vehicle re-identification	4
Point Mask Transformer for Outdoor Point Cloud Semantic Segmentation	4
Polygonal finite element-based content-aware image warping	4
AR assistance for efficient dynamic target search	4
LDSwap: A Semantic-Related Latent Code Disentangling Method in StyleSpace Towards High-Resolution Face Swapping	3
BLNet: Bidirectional learning network for point clouds	3
Emotion Amplification of Facial Videos Using a Fine-Tuned StyleGAN	3
Multi-modal visual tracking: Review and experimental comparison	3
PMSSC: Parallelizable multi-subset based self-expressive model for subspace clustering	3
A survey on rendering homogeneous participating media	3
Foundation models meet visualizations: Challenges and opportunities	3
Multi-Task Gradual Inference with a Single Encoder–Decoder Network for Automatic Portrait Matting	3
A comprehensive survey on the research and development of RGB-T salient object detection	3
Message from the best paper award committee	3
Swin3D++: Effective Multi-Source Pretraining for 3D Indoor Scene Understanding	3
Class Incremental Learning via Feature Space Calibration	3
Angle-uniform parallel coordinates	3
CLIP-SP: Vision-language model with adaptive prompting for scene parsing	3
Full-duplex strategy for video object segmentation	3
GRIG: Data-Efficient Generative Residual Image Inpainting	3
ARNet: Attribute Artifact Reduction for G-PCC Compressed Point Clouds	3
Swin3D: A Pretrained Transformer Backbone for 3D Indoor Scene Understanding	2
Recent advances in 3D Gaussian splatting	2
RecStitchNet: Learning to stitch images with rectangular boundaries	2
Active self-training for weakly supervised 3D scene semantic segmentation	2
Specificity-preserving RGB-D saliency detection	2
JVCSR+: Adaptively Learned Video Compressive Sensing Reconstruction with Joint in-Loop Reference Enhancement and Out-Loop Super-Resolution	2
HoLens: A visual analytics design for higher-order movement modeling and visualization	2
Spatiotemporal Fusion Transformer for Video Demoiréing	2
Self-supervised coarse-to-fine monocular depth estimation using a lightweight attention module	2
Remote Sensing Tuning: A Survey	2
Decoupled Two-Stage Talking Head Generation via Gaussian-Landmark-Based Neural Radiance Fields	2
Contents	2
Sequential interactive image segmentation	2
Discriminative feature encoding for intrinsic image decomposition	2
Dance2MIDI: Dance-driven multi-instrument music generation	2
Taming diffusion model for exemplar-based image translation	2
Progressive edge-sensing dynamic scene deblurring	2
FastMAE: Efficient Masked Autoencoder with Offline Tokenizer	2
Audio-guided implicit neural representation for local image stylization	2
Transformers in computational visual media: A survey	2
Computer-Aided Layout Generation for Building Design: A Review	2
Rectangling irregular videos by optimal spatio-temporal warping	2
Class-conditional domain adaptation for semantic segmentation	2
Contents	2