OOIR: Observatory of International Research

Papers

(The median citation count of Computational Visual Media is 3. 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 2022-08-01 to 2026-08-01.)

Article	Citations
Geometry-aware 3D pose transfer using transformer autoencoder	2263
Ultra-High Resolution Facial Texture Reconstruction from a Single Image	2171
MA2Net: Multi-Scale Adaptive Mixed Attention Network for Image Demoiréing	885
Front Cover	217
Towards harmonized regional style transfer and manipulation for facial images	106
3D face recognition: A comprehensive survey in 2022	86
PE Loss: Perception-Enhanced Distortion-Oriented Loss for Image Restoration	83
3D Indoor Scene Geometry Estimation from a Single Omnidirectional Image: A Comprehensive Survey	80
Heuristic Weakly Supervised 3D Human Pose Estimation	76
A Biophysical-Based Skin Model for Heterogeneous Volume Rendering	70
Front Cover	64
Recent advances in glinty appearance rendering	55
FRNeRF: Fusion and Regularization Fields for Dynamic View Synthesis	45
Controllable multi-domain semantic artwork synthesis	45
Real-Time Woven Fabric Rendering Using SGGX Fitting	38
A causal convolutional neural network for multi-subject motion modeling and generation	32
Towards robustness and generalization of point cloud representation: A geometry coding method and a large-scale object-level dataset	28
Temporal vectorized visibility for direct illumination of animated models	27
Central similarity consistency hashing for asymmetric image retrieval	26
Neural Scene Baking for Permutation Invariant Transparency Rendering with Real-Time Global Illumination	26
Anchor-Regularized GAN Priors	26
See More, Know More: Richer Prior Knowledge for Novel Class Discovery	26
Practical construction of globally injective parameterizations with positional constraints	22
Neural Reconstruction and Super-Resolution for Foveated Real-Time Rendering	22
Multi-granularity sequence generation for hierarchical image classification	22

Image-guided color mapping for categorical data visualization	22
Self-Supervised Learning for Pre-Training 3D Point Clouds: A Survey	21
IIDM: Image-to-Image Diffusion Model for Semantic Image Synthesis	20
Contents	19
D2ANet: Difference-aware attention network for multi-level change detection from satellite imagery	17
MusicFace: Music-driven expressive singing face synthesis	17
Photorealistic Fire Scene Video Generation via Multimodal Large Language Model and Pre-Trained Video Diffusion Model	17
ARM3D: Attention-based relation module for indoor 3D object detection	17
Message from Guest Editors of the CVM 2025 Special Issue	16
Real-time distance field acceleration based free-viewpoint video synthesis for large sports fields	16
DepthGAN: GAN-based depth generation from semantic layouts	16
Front Cover	15
NeuS-PIR: Learning Relightable Neural Surface Using Pre-Integrated Rendering	15
A survey of urban visual analytics: Advances and future directions	14
Multi3D: 3D-aware multimodal image synthesis	14
Let's all dance: Enhancing amateur dance motions	13
Sphere face model: A 3D morphable model with hypersphere manifold latent space using joint 2D/3D training	13
Watertight surface reconstruction method for CAD models based on optimal transport	12
Prediction of Scene Plausibility	12
Constructing self-supporting surfaces with planar quadrilateral elements	12
MMRelief: Modeling Multi-Human Relief from a Single Photograph	11
Global video object segmentation with spatial constraint module	11
Deep unfolding multi-scale regularizer network for image denoising	11
Benchmarking visual SLAM methods in mirror environments	11
Sem-iNeRF: Camera Pose Refinement by Inverting Neural Radiance Fields with Semantic Feature Consistency	11
MDFP-Net: A Model-Driven Deep Neural Network for Fourier Ptychography	11
Mindstorms in Natural Language-Based Societies of Mind	11
Uncertainty Aware Multiple View Stereo Network with Accurate Supervision	11
Addressing Missing Modality Challenges in MRI Images: A Comprehensive Review	11
A Voronoi diagram approach for detecting defects in 3D printed fiber-reinforced polymers from microscope images	10
Front cover	10
EG-HumanNeRF: Efficient Generalizable Human NeRF Utilizing Human Prior for Sparse View	10
Neural video field editing	10
EFECL: Feature encoding enhancement with contrastive learning for indoor 3D object detection	10
Exploring Contextual Priors for Real-World Image Super-Resolution	10
Continuous Indexed Points for Multivariate Volume Visualization	9
FCDFusion: A Fast, Low Color Deviation Method for Fusing Visible and Infrared Image Pairs	9
Hybrid Mesh-Neural Representation for 3D Transparent Object Reconstruction	9
Front cover	9
SMixNet: Style Mixture Network for Exemplar-Based Image Translation	9
A two-step surface-based 3D deep learning pipeline for segmentation of intracranial aneurysms	9
Deep panoramic depth prediction and completion for indoor scenes	9
Contents	9
Contents	9
SGformer: Boosting transformers for indoor lighting estimation from a single image	9
Point cloud completion via structured feature maps using a feedback network	8
Z-STAR+: A zero-shot style transfer method adjusting style distribution	8
Focusing on your subject: Deep subject-aware image composition recommendation networks	8
PuzzleSorter: Certainty-Aware Visual Restoration of Multiple Cultural Artifacts	8
Front cover	8

Immersive Analytics Meets Artificial Intelligence: A Systematic Review	8
A survey on facial image deblurring	8
Dynamic ocean inverse modeling based on differentiable rendering	8
An efficient algorithm for approximate Voronoi diagram construction on triangulated surfaces	8
Joint specular highlight detection and removal in single images via Unet-Transformer	8
Towards uniform point distribution in feature-preserving point cloud filtering	7
A Simple and Effective Filtering Scheme for Improving Neural Fields	7
An anisotropic Chebyshev descriptor and its optimization for deformable shape correspondence	7
Revitalizing Image Dehazing in the Real World: A High-Quality Dataset and a Customized Method	7
A visual modeling method for spatiotemporal and multidimensional features in epidemiological analysis: Applied COVID-19 aggregated datasets	7
Contents	7
Message from the editor-in-chief	7
Open-Vocabulary Camouflaged Object Segmentation with Cascaded Vision Language Models	7
Cross-modal learning using privileged information for long-tailed image classification	7
PVT v2: Improved baselines with pyramid vision transformer	6
ImVoxelENet: Image to Voxels Epipolar Transformer for Multi-View RGB-Based 3D Object Detection	6
MagicTalk: Implicit and Explicit Correlation Learning for Diffusion-Based Emotional Talking Face Generation	6
Attention mechanisms in computer vision: A survey	6
Front Cover	6
NPRportrait 1.0: A three-level benchmark for non-photorealistic rendering of portraits	6
Super-resolution reconstruction of single image for latent features	6
Message from the editor-in-chief	6
Exploring a Hierarchical Cross-Attention Transformer for High-Speed Tracking	6
Front cover	6
FilterGNN: Image feature matching with cascaded outlier filters and linear attention	6
Continual few-shot patch-based learning for anime-style colorization	6
Lossless Intrinsic Image Decomposition via Learning Shading Feature Filtering	5
Multi-Color Compressive Hologram Synthesis with Learned Wave Propagation	5
Autocompletion of repetitive stroking with image guidance	5
Polygonal finite element-based content-aware image warping	5
Point Mask Transformer for Outdoor Point Cloud Semantic Segmentation	5
FEDNet: A Feature-Enhanced Diffusion Network for Efficient and Universal Texture Synthesis	5
PraNet-V2: Dual-Supervised Reverse Attention for Medical Image Segmentation	5
BoostPoint: Boosting Point Cloud Backbones with Image Pre-Training for 3D Understanding	5
JNeRF: An efficient heterogeneous NeRF model zoo based on Jittor	5
Full-duplex strategy for video object segmentation	4
Noise4Denoise: Leveraging noise for unsupervised point cloud denoising	4
Emotion Amplification of Facial Videos Using a Fine-Tuned StyleGAN	4
A Comprehensive Survey on the Research and Development of RGB-T Salient Object Detection	4
Message from the best paper award committee	4
PMSSC: Parallelizable multi-subset based self-expressive model for subspace clustering	4
SAM-driven MAE pre-training and background-aware meta-learning for unsupervised vehicle re-identification	4
Pyramid-Angular-Constraint Network for Light Field Super-Resolution	4
CLIP-SP: Vision-language model with adaptive prompting for scene parsing	4
Multi-modal visual tracking: Review and experimental comparison	4
GRIG: Data-Efficient Generative Residual Image Inpainting	4
Multi-level dynamic style transfer for NeRFs	4
Learning physically based material and lighting decompositions for face editing	4
AR assistance for efficient dynamic target search	4
LucIE: Language-Guided Local Image Editing for Fashion Images	4
BLNet: Bidirectional learning network for point clouds	4
Multi-Task Gradual Inference with a Single Encoder–Decoder Network for Automatic Portrait Matting	4
Swin3D: A Pretrained Transformer Backbone for 3D Indoor Scene Understanding	3
A benchmark for 3D mesh denoising	3
Class Incremental Learning via Feature Space Calibration	3
Recent advances in 3D Gaussian splatting	3
Class-conditional domain adaptation for semantic segmentation	3
Spatiotemporal Fusion Transformer for Video Demoiréing	3
Audio-guided implicit neural representation for local image stylization	3
Taming diffusion model for exemplar-based image translation	3
Foundation models meet visualizations: Challenges and opportunities	3
ARNet: Attribute Artifact Reduction for G-PCC Compressed Point Clouds	3
LDSwap: A Semantic-Related Latent Code Disentangling Method in StyleSpace Towards High-Resolution Face Swapping	3
Angle-uniform parallel coordinates	3
Contents	3
Contents	3
FedDTR: Leveraging intra-domain global priors via domain-invariant text representation for personalized federated learning	3
Self-supervised coarse-to-fine monocular depth estimation using a lightweight attention module	3
Swin3D++: Effective Multi-Source Pretraining for 3D Indoor Scene Understanding	3
Neural radiance fields in 3D vision: A comprehensive review	3
Rethinking medical VQA models: Towards data-efficient learning	3
FastMAE: Efficient Masked Autoencoder with Offline Tokenizer	3
Decoupled Two-Stage Talking Head Generation via Gaussian-Landmark-Based Neural Radiance Fields	3
Remote Sensing Tuning: A Survey	3
Progressive edge-sensing dynamic scene deblurring	3