CVPR 2021

2,096 papers

Top Research Directions

Research directions most represented by CVPR 2021 papers.

Generalizing from Synthetic Data to the Real World 40
Resolving Depth Ambiguity in Monocular 3D Reconstruction 22
Accelerating Neural Architecture Search Without Full Model Training 20
Mitigating Error Propagation in Pseudo Labeling 19
Global Context Modeling via Non-Local Spatial Attention 18
Disentangling Attribute Control in Generative Models 17
Loss Weighting via Predictive Uncertainty 17
Why Theoretical FLOPs Fail to Predict Real Latency 17
Generative Hallucination for Disoccluded Region Synthesis 17
Deep Learning on Unstructured 3D Point Clouds 17
Preserving Tiny Features Against Spatial Resolution Degradation 16
Reconstructing Complete Geometry from Partial Point Clouds 16
The Sensitivity of Multi-Objective Loss Balancing 16
Cross Task Generalization in Image Restoration 15
Overcoming the Static Scene Assumption 15

Top Authors

AuthorPapers
Luc Van Gool15
Chunhua Shen13
Dacheng Tao12
Chang Xu11
Chen Change Loy11
Ling Shao11
Yi Yang11
Jiaya Jia10
Marc Pollefeys10
Ziwei Liu10
Alan Yuille9
Hongsheng Li9
Jie Zhou9
Yunhe Wang9
Christian Theobalt8
Hongdong Li8
Houqiang Li8
Huchuan Lu8
Lei Zhang8
Leonidas Guibas8

Impactful Papers

Papers from CVPR 2021 that shaped research clusters.

Foundational

Influential

Papers

Title
Neural Parts: Learning Expressive 3D Shape Abstractions With Invertible Neural Networks
Neural Point Light Fields
Neural Prototype Trees for Interpretable Fine-Grained Image Recognition
Neural Rays for Occlusion-aware Image-based Rendering
NeuralRecon: Real-Time Coherent 3D Reconstruction From Monocular Video
Neural Reprojection Error: Merging Feature Learning and Camera Pose Estimation
Neural Response Interpretation Through the Lens of Critical Pathways
Neural RGB-D Surface Reconstruction
Neural Scene Flow Fields for Space-Time View Synthesis of Dynamic Scenes
Neural Scene Graphs for Dynamic Scenes
Neural Side-by-Side: Predicting Human Preferences for No-Reference Super-Resolution Evaluation
Neural Splines: Fitting 3D Surfaces With Infinitely-Wide Neural Networks
Neural Surface Maps
NeuroMorph: Unsupervised Shape Interpolation and Correspondence in One Go
NeuTex: Neural Texture Mapping for Volumetric Neural Rendering
NewtonianVAE: Proportional Control and Goal Identification From Pixels via Physical Latent Spaces
NeX: Real-Time View Synthesis With Neural Basis Expansion
NExT-QA: Next Phase of Question-Answering to Explaining Temporal Actions
NICE-SLAM: Neural Implicit Scalable Encoding for SLAM
Nighttime Visibility Enhancement by Increasing the Dynamic Range and Suppression of Light Effects
No Frame Left Behind: Full Video Action Recognition
Noise Distribution Adaptive Self-Supervised Image Denoising using Tweedie Distribution and Score Matching
Noise-Resistant Deep Metric Learning With Ranking-Based Instance Selection
NomMer: Nominate Synergistic Context in Vision Transformer for Visual Recognition
Non-Salient Region Object Mining for Weakly Supervised Semantic Segmentation
Nonuniform-to-Uniform Quantization: Towards Accurate Quantization via Generalized Straight-Through Estimation
No-Reference Point Cloud Quality Assessment via Domain Adaptation
NormalFusion: Real-Time Acquisition of Surface Normals for High-Resolution RGB-D Scanning
Normal Integration via Inverse Plane Fitting With Minimum Point-to-Plane Distance
Normalized Avatar Synthesis Using StyleGAN and Perceptual Refinement
No Shadow Left Behind: Removing Objects and Their Shadows Using Approximate Lighting and Geometry
Not All Labels Are Equal: Rationalizing The Labeling Costs for Training Object Detection
Novel Class Discovery in Semantic Segmentation
NPAS: A Compiler-Aware Framework of Unified Network Pruning and Architecture Search for Beyond Real-Time Mobile Acceleration
NTIRE 2021 Challenge for Defocus Deblurring Using Dual-Pixel Images: Methods and Results
NTIRE 2021 Challenge on Burst Super-Resolution: Methods and Results
NTIRE 2021 Challenge on Perceptual Image Quality Assessment
NTIRE 2021 Challenge on Video Super-Resolution
NTIRE 2021 Learning the Super-Resolution Space Challenge
NTIRE 2021 NonHomogeneous Dehazing Challenge Report
Nutrition5k: Towards Automatic Nutritional Understanding of Generic Food
Object-aware Video-language Pre-training for Retrieval
Object Classification From Randomized EEG Trials
Object-Region Video Transformers
Objectron: A Large Scale Dataset of Object-Centric Videos in the Wild With Pose Annotations
Objects Are Different: Flexible Monocular 3D Object Detection
OBoW: Online Bag-of-Visual-Words Generation for Self-Supervised Learning
OCONet: Image Extrapolation by Object Completion
Offboard 3D Object Detection From Point Cloud Sequences
OmniLayout: Room Layout Reconstruction From Indoor Spherical Panoramas

« prev Page 26/42 next »