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 2021-02-01 to 2025-02-01.)

Article	Citations
PVT v2: Improved baselines with Pyramid Vision Transformer	1174
Attention mechanisms in computer vision: A survey	1034
Robust and efficient edge-based visual odometry	950
Flow-aware synthesis: A generic motion model for video frame interpolation	313
Transformers in computational visual media: A survey	85
Deep image synthesis from intuitive user input: A review and perspectives	48
RecStitchNet: Learning to stitch images with rectangular boundaries	40
Improved fuzzy clustering for image segmentation based on a low-rank prior	36
Efficient fastest-path computations for road maps	36
Message from the Editor-in-Chief	30
Towards harmonized regional style transfer and manipulation for facial images	29
Temporal and spatial anti-aliasing for rendering reflections on water waves	24
APF-GAN: Exploring asymmetric pre-training and fine-tuning strategy for conditional generative adversarial network	21
Neural 3D reconstruction from sparse views using geometric priors	20
Improved image denoising via RAISR with fewer filters	20
Multi-task learning and joint refinement between camera localization and object detection	19
Geometry-aware 3D pose transfer using transformer autoencoder	17
Continual few-shot patch-based learning for anime-style colorization	16
Illuminator: Image-based illumination editing for indoor scene harmonization	16
EFECL: Feature encoding enhancement with contrastive learning for indoor 3D object detection	16
Rendering discrete participating media using geometrical optics approximation	15
Deep panoramic depth prediction and completion for indoor scenes	14
A Voronoi diagram approach for detecting defects in 3D printed fiber-reinforced polymers from microscope images	14
3D face recognition: A comprehensive survey in 2022	13
DualSmoke: Sketch-based smoke illustration design with two-stage generative model	13

Physics-based fluid simulation in computer graphics: Survey, research trends, and challenges	13
[Front Cover]	12
Delving into high-quality SVBRDF acquisition: A new setup and method	12
Class-conditional domain adaptation for semantic segmentation	12
Adaptive sampling and reconstruction for gradient-domain rendering	12
3D corrective nose reconstruction from a single image	11
Towards natural object-based image recoloring	11
A two-step surface-based 3D deep learning pipeline for segmentation of intracranial aneurysms	11
Neighborhood co-occurrence modeling in 3D point cloud segmentation	11
Autocompletion of repetitive stroking with image guidance	10
Joint self-supervised and reference-guided learning for depth inpainting	10
JNeRF: An efficient heterogeneous NeRF model zoo based on Jittor	9
Controllable multi-domain semantic artwork synthesis	9
Can attention enable MLPs to catch up with CNNs?	9
NPRportrait 1.0: A three-level benchmark for non-photorealistic rendering of portraits	9
AdaPIP: Adaptive picture-in-picture guidance for 360° film watching	8
Mask-aware photorealistic facial attribute manipulation	8
Message from the Editor-in-Chief	8
Recent advances in glinty appearance rendering	8
Low and non-uniform illumination color image enhancement using weighted guided image filtering	8
SAM-driven MAE pre-training and background-aware meta-learning for unsupervised vehicle re-identification	7
Automatic location and semantic labeling of landmarks on 3D human body models	7
Polygonal finite element-based content-aware image warping	7
Multi-scale hash encoding based neural geometry representation	7
DeepFaceReshaping: Interactive deep face reshaping via landmark manipulation	7
Dance2MIDI: Dance-driven multi-instrument music generation	7
Noise4Denoise: Leveraging noise for unsupervised point cloud denoising	7
Discriminative feature encoding for intrinsic image decomposition	6
Specificity-preserving RGB-D saliency detection	6
HoLens: A visual analytics design for higher-order movement modeling and visualization	6
SGformer: Boosting transformers for indoor lighting estimation from a single image	6
Shape embedding and retrieval in multi-flow deformation	6
Learning physically based material and lighting decompositions for face editing	6
PCT: Point cloud transformer	5
CLIP-Flow: Decoding images encoded in CLIP space	5
Learning accurate template matching with differentiable coarse-to-fine correspondence refinement	5
Message from the Editor-in-Chief	5
EfficientPose: Efficient human pose estimation with neural architecture search	5
3D hand pose and shape estimation from monocular RGB via efficient 2D cues	5
Learning conditional photometric stereo with high-resolution features	5
Hierarchical vectorization for facial images	5
Dynamic ocean inverse modeling based on differentiable rendering	4
Full-duplex strategy for video object segmentation	4
Learning layout generation for virtual worlds	4
Temporal vectorized visibility for direct illumination of animated models	4
Practical construction of globally injective parameterizations with positional constraints	4
Multi-granularity sequence generation for hierarchical image classification	4
Central similarity consistency hashing for asymmetric image retrieval	4
A causal convolutional neural network for multi-subject motion modeling and generation	3
Symmetrization of quasi-regular patterns with periodic tilting of regular polygons	3

Image-guided color mapping for categorical data visualization	3
Bin-scanning: Segmentation of X-ray CT volume of binned parts using Morse skeleton graph of distance transform	3
AR assistance for efficient dynamic target search	3
CF-DAN: Facial-expression recognition based on cross-fusion dual-attention network	3
Towards robustness and generalization of point cloud representation: A geometry coding method and a large-scale object-level dataset	3
Semi-supervised 3D shape segmentation with multilevel consistency and part substitution	3
Point cloud completion via structured feature maps using a feedback network	3
Shape correspondence for cel animation based on a shape association graph and spectral matching	3
TrafPS: A shapley-based visual analytics approach to interpret traffic	3
CLIP-SP: Vision-language model with adaptive prompting for scene parsing	3
Sequential interactive image segmentation	3
Multi-modal visual tracking: Review and experimental comparison	3
SiamCPN: Visual tracking with the Siamese center-prediction network	2
ARM3D: Attention-based relation module for indoor 3D object detection	2
Real-time face view correction for front-facing cameras	2
Temporally consistent video colorization with deep feature propagation and self-regularization learning	2
PMSSC: Parallelizable multi-subset based self-expressive model for subspace clustering	2
Message from the Best Paper Award Committee	2
Pyramid-VAE-GAN: Transferring hierarchical latent variables for image inpainting	2
Active self-training for weakly supervised 3D scene semantic segmentation	2
CTSN: Predicting cloth deformation for skeleton-based characters with a two-stream skinning network	2
High-quality indoor scene 3D reconstruction with RGB-D cameras: A brief review	2
See clearly on rainy days: Hybrid multiscale loss guided multi-feature fusion network for single image rain removal	2
Rectangling irregular videos by optimal spatio-temporal warping	2
Non-dominated sorting based multi-page photo collage	2
An efficient algorithm for approximate Voronoi diagram construction on triangulated surfaces	2
High fidelity virtual try-on network via semantic adaptation and distributed componentization	2