Skip to content

Latest commit

 

History

History
 
 

vision

Folders and files

NameName
Last commit message
Last commit date

parent directory

..
 
 

Vision Papers

A list of papers from vision conferences such as CVPR, ECCV, and ICCV

CVPR

  • CVPR2020 Differentiable Volumetric Rendering: Learning Implicit 3D Representations without 3D Supervision [code]
  • CVPR2020 StegaStamp: Invisible Hyperlinks in Physical Photographs [code]
  • CVPR2020 Lighthouse: Predicting Lighting Volumes for Spatially-Coherent Illumination [code]
  • CVPR2020 CNN-generated images are surprisingly easy to spot... for now [code]
  • CVPR2020 End-to-End Time-Lapse Video Synthesis from a Single Outdoor Image
  • CVPR2020 Learning to Cartoonize Using White-box Cartoon Representations [code]
  • CVPR2020 Dreaming to Distill: Data-free Knowledge Transfer via DeepInversion [code][link]
  • CVPR2020 Lighthouse: Predicting Lighting Volumes for Spatially-Coherent Illumination [code]
  • CVPR2020 StegaStamp: Invisible Hyperlinks in Physical Photographs [code]
  • CVPR2020 Inverse Rendering for Complex Indoor Scenes: Shape, Spatially-Varying Lighting and SVBRDF from a Single Image [link]
  • CVPR2020 Intuitive, Interactive Beard and Hair Synthesis with Generative Models [link]
  • CVPR2020 Deep 3D Capture: Geometry and Reflectance from Sparse Multi-View Images [link]
  • CVPR2020 DeepStrip: High Resolution Boundary Refinement [link]
  • CVPR2020 Prior Guided GAN Based Semantic Inpainting [link]
  • CVPR2020 Diverse Image Generation via Self-Conditioned GANs [link]
  • CVPR2020 Contextual Residual Aggregation for Ultra High-Resolution Image Inpainting [link][code]
  • CVPR2020 StyleRig: Rigging StyleGAN for 3D Control over Portrait Images [link]
  • CVPR2020 Self-Supervised Viewpoint Learning from Image Collections [code]
  • CVPR2020 Deep Iterative Collaboration for Face Super-Resolution [code]
  • CVPR2020 AdaCoF: Adaptive Collaboration of Flows for Video Frame Interpolation [code]
  • CVPR2020 DeepLPF: Deep Local Parametric Filters for Image Enhancement [code]
  • CVPR2020 3D Photography using Context-aware Layered Depth Inpainting [code]
  • CVPR2020 Self-Supervised Scene De-occlusion [code]
  • CVPR2020 Neural Voxel Renderer [link]
  • CVPR2020 Neural Point-based Grpahics [link][code]
  • CVPR2020 Single-Image HDR Reconstruction by Learning to Reverse the Camera Pipeline [code]
  • CVPR2020 Image Processing Using Multi-Code GAN Prior [code]
  • CVPR2020 Background Matting: The World is Your Green Screen [code]
  • CVPR2020 PIFuHD: Multi-Level Pixel-Aligned Implicit Function for High-Resolution 3D Human Digitization [code]
  • CVPR2020 Lightweight Photometric Stereo for Facial Details Recovery [code]
  • CVPR2020 DISN: Deep Implicit Surface Network for High-quality Single-view 3D Reconstruction [code]
  • CVPR2020 High-Resolution Daytime Translation Without Domain Labels [code]
  • CVPR2020 Adversarial Texture Optimization from RGB-D Scans [code]
  • CVPR2020 Rotate-and-Render: Unsupervised Photorealistic Face Rotation from Single-View Images [code]
  • CVPR2020 GAN Compression: Efficient Architectures for Interactive Conditional GANs [link]
  • CVPR2020 SwapText: Image Based Texts Transfer in Scenes [link]
  • CVPR2020 Softmax Splatting for Video Frame Interpolation [code]
  • CVPR2020 Learning Physics-guided Face Relighting under Directional Light [link]
  • CVPR2020 Reinforced Feature Points:Optimizing Feature Detection and Description for a High-Level Task [link]
  • CVPR2020 Novel View Synthesis of Dynamic Scenes with Globally Coherent Depths [link]
  • CVPR2020 Deep Image Spatial Transformation for Person Image Generation
  • CVPR2020 Learning to Shadow Hand-drawn Sketches [link]
  • CVPR2019 Joint Face Detection and Facial Motion Retargeting for Multiple Faces [link]
  • CVPR2019 Texture Mixer: A Network for Controllable Synthesis and Interpolation of Texture [code]
  • CVPR2019 Pushing the Boundaries of View Extrapolation with Multiplane Images [code]
  • CVPR2019 Spatial Fusion GAN for Image Synthesis [link]
  • CVPR2019 Self-Supervised Adaptation of High-Fidelity Face Models for Monocular Performance Tracking [link]
  • CVPR2019 WarpGAN: Automatic Caricature Generation [link][code]
  • CVPR2019 Deep Image Prior [link][code]
  • CVPR2019 Total Scene Capture: Neural Rerendering in the Wild [link] [code]
  • CVPR2019 Fast Spatially-Varying Indoor Lighting Estimation [link]
  • CVPR2019 Neural Illumination: Lighting Prediction for Indoor Environments [link]
  • CVPR2019 Deep Sky Modeling for Single Image Outdoor Lighting Estimation [link]
  • CVPR2019 Semantic Image Synthesis with Spatially-Adaptive Normalization [link] [code]
  • CVPR2019 DeepView: View synthesis with learned gradient descent [link] [code]
  • CVPR2019 Animating Arbitrary Objects via Deep Motion Transfer [link] [code]
  • CVPR2019 Textured Neural Avatars [link] [code]
  • CVPR2019 IM-Net for High Resolution Video Frame Interpolation [link] [code]
  • CVPR2019 "Double-DIP": Unsupervised Image Decomposition via Coupled Deep-Image-Priors [link] [code]
  • CVPR2018 Single Image Reflection Removal with Perceptual Losses [link] [code]
  • CVPR2018 Deep Marhcing Cubes [code]
  • CVPR2018 Neural 3D Mesh Renderer [link][code]

ICCV

  • ICCV2019 SinGAN: Learning a Generative Model from a Single Natural Image [code]
  • ICCV2019 InGAN: Capturing and Retargeting the DNA of a Natural Image [code]
  • ICCV2019 Image2StyleGAN: How to Embed Images Into the StyleGAN Latent Space? [link]
  • ICCV2019 Specifying Object Attributes and Relations in Interactive Scene Generation [code]
  • ICCV2019 FaceForensics++: Learning to Detect Manipulated Facial Images [code]
  • ICCV2019 StructureFlow: Image Inpainting via Structure-Aware Appearance Flow [code]
  • ICCV2019 Generative Adversarial Training for Weakly Supervised Cloud Matting [link]
  • ICCV2019 Indices Matter: Learning to Index for Deep Image Matting[code]
  • ICCV2019 Seeing Motion in the Dark [link]
  • ICCV2019 FSGAN: Subject Agnostic Face Swapping and Reenactment [link]
  • ICCV2019 Gaze360: Physically Unconstrained Gaze Estimation in the Wild [link][code]
  • ICCV2019 Learning Perspective Undistortion of Portraits [code]
  • ICCV2019 Neural Re-Simulation for Generating Bounces in Single Images [link]
  • ICCV2019 Neural Inverse Rendering of an Indoor Scene From a Single Image [link]
  • ICCV2019 Dynamic-Net: Tuning the Objective Without Re-Training for Synthesis Tasks [link][code]
  • ICCV2019 Boundless: Generative Adversarial Networks for Image Extension [link]
  • ICCV2019 Few-Shot Unsupervised Image-to-Image Translation [code]
  • ICCV2019 Very Long Natural Scenery Image Prediction by Outpainting [code]
  • ICCV2019 Deep CG2Real: Synthetic-to-Real Translation via Image Disentanglement [link]
  • ICCV2019 PIFu: Pixel-Aligned Implicit Function for High-Resolution Clothed Human Digitization [coe]
  • ICCV2019 Learning Deep Priors for Image Dehazing [link]
  • ICCV2019 An Internal Learning Approach to Video Inpainting [code]
  • ICCV2019 Neural-Guided RANSAC: Learning Where to Sample Model Hypotheses[code]
  • ICCV2019 Multi-View Image Fusion [link]
  • ICCV2019 Onion-Peel Networks for Deep Video Completion [code
  • ICCV2019 Copy-and-Paste Networks for Deep Video Inpainting [code]
  • ICCV2019 Deep Parametric Indoor Lighting Estimation [link]
  • ICCV2019 Everybody Dance Now [link]
  • ICCV2019 Extreme View Synthesis [code]
  • ICCV2019 Three-D Safari: Learning to Estimate Zebra Pose, Shape, and Texture From Images “In the Wild” [code]
  • ICCV2019 Unsupervised Video Interpolation Using Cycle Consistency [code]

ECCV

  • ECCV2020 Learning Joint Spatial-Temporal Transformations for Video Inpainting [code]
  • ECCV2020 Proposal based Video Completion [link][code]
  • ECCV2020 Flow-edge Guided Video Completion [link][code]
  • ECCV2020 Rethinking image inpainting via a mutual encoder-decoder with feature equalization [link][code]
  • ECCV2020 DVI: Depth Guided Video Inpainting for Autonomous Driving [link][code]
  • ECCV2020 Deep Space-Time Video Upsampling Networks [link][code]
  • ECCV2020 Defocus Blur Detection via Depth Distillation [code]
  • ECCV2020 From Shadow Segmentation to Shadow Removal [link][code]
  • ECCV2020 Filter Style Transfer between Photos [link][code]
  • ECCV2020 Invertible Image Rescaling [code]
  • ECCV2020 Rewriting a Deep Generative Model [link][code]
  • ECCV2020 MatryODShka: Real-time 6DoF Video View Synthesis using Multi-Sphere Images [link]
  • ECCV2020 Unsupervised Sketch-to-Photo Synthesis [link][code]
  • ECCV2020 DTVNet: Dynamic Time-lapse Video Generation via Single Still Image [code]
  • ECCV2020 BMBC:Bilateral Motion Estimation with Bilateral Cost Volume for Video Interpolation [link][code]
  • ECCV2020 Colorization of Depth Map via Disentanglement [link][code]
  • ECCV2020 Controllable Image Synthesis via SegVAE [link][code]
  • ECCV2020 CooGAN: A Memory-Efficient Framework for High-Resolution Facial Attribute Editing [link][code]
  • ECCV2020 DeepLandscape: Adversarial Modeling of Landscape Video [code]
  • ECCV2020 High-Resolution Image Inpainting with Iterative Confidence Feedback and Guided Upsampling [link][code]
  • ECCV2020 In-Domain GAN Inversion for Real Image Editing [link][code]
  • ECCV2020 Lifespan Age Transformation Synthesis [link][code]
  • ECCV2020 Neural Hair Rendering [link][code]
  • ECCV2020 Neural Re-Rendering of Humans from a Single Image [link]
  • ECCV2020 Novel View Synthesis on Unpaired Data by Conditional Deformable Variational Auto-Encoder [link][code]
  • ECCV2020 StyleGAN2 Distillation for Feed-forward Image Manipulation [code]
  • ECCV2020 Talking-head Generation with Rhythmic Head Motion [code]
  • ECCV2020 Unpaired Image-to-Image Translation using Adversarial Consistency Loss [link][code]
  • ECCV2020 Unselfie: Translating Selfies to Neutral-pose Portraits in the Wild [link][code]
  • ECCV2020 World-Consistent Video-to-Video Synthesis [link][code]
  • ECCV2020 Learning Stereo from Single Images [code]
  • ECCV2020 Occlusion-Aware Depth Estimation with Adaptive Normal Constraints [link][code]
  • ECCV2020 Synthesis and Completion of Facades from Satellite Imagery [link][code]
  • ECCV2020 Learning to Factorize a City [link][code]
  • ECCV2020 BézierSketch: A generative model for scalable vector sketches [link][code]
  • ECCV2020 AutoSimulate: (Quickly) Learning Synthetic Data Generation [link]
  • ECCV2020 Contrastive Learning for Conditional Image Generation [link][code]
  • ECCV2020 Curriculum DeepSDF [code]
  • ECCV2020 Deep Multi Depth Panoramas for View Synthesis [link][code]
  • ECCV2020 Deformable Style Transfer [link]
  • ECCV2020 Hierarchical Style-based Networks for Motion Synthesis [link][code]
  • ECCV2020 High Resolution Zero-Shot Domain Adaptation of Synthetically Rendered Face Images [link][code]
  • ECCV2020 SG-VAE: Scene Grammar Variational Autoencoder to generate new indoor scenes [link][code]
  • ECCV2020 Self-supervised Outdoor Scene Relighting [link][code]
  • ECCV2020 Who left the dogs out? 3D Animal Reconstruction with Expectation Maximization in the Loop [link][code]
  • ECCV2020 Long-term Human Motion Prediction with Scene Context [link]
  • ECCV2020 Reconstructing NBA Players [link]
  • ECCV2020 Crowdsampling The Plenoptic Function [link]
  • ECCV2020 Contrastive Learning for Unpaired Image-to-Image Translation [link][code]
  • ECCV2020 Learning Joint Spatial-Temporal Transformations for Video Inpainting [link]
  • ECCV2020 Lifespan Age Transformation Synthesis [link]
  • ECCV2020 RANSAC-Flow: generic two-stageimage alignment [code]
  • ECCV2020 Contact and Human Dynamics from Monocular Video [link]
  • ECCV2020 Learning to Factorize and Relight a City [link]
  • ECCV2020 NASA: Neural Articulated Shape Approximation [link]
  • ECCV2020 People as Scene Probes [link]
  • ECCV2020 COCO-FUNIT: Few-Shot Unsupervised Image Translation with a Content Conditioned Style Encoder [link]
  • ECCV2020 JWorld-Consistent Video-to-Video Synthesis [link]
  • ECCV2020 JNR: Joint-based Neural Rig Representation for Compact 3D Face Modeling
  • ECCV2020 Personalized Face Modeling for Improved Face Reconstruction and Motion Retargeting
  • ECCV2020 Neural Point-Based Graphics [code]
  • ECCV2020 NeRF: Representing Scenes as Neural Radiance Fields for View Synthesis [code]
  • ECCV2018 GANimorph: Improving Shape Deformation in Unsupervised Image to Image Translation [link][code]
  • ECCV2018 CGIntrinsics: Better Intrinsic Image Decomposition through Physically-Based Rendering [link][code]

ETC

  • CVPRW2020 The “Vertigo Effect” on Your Smartphone:Dolly Zoom via Single Shot View Synthesis [link]
  • CVPRW2020 Sky Optimization: Semantically aware image processing of skies in low-light photography [code]
  • ICRA2020 DREAM: Camera Calibration without Fiducial Markers through Sim2Real Keypoint Detection [code]
  • arxiv2020 SIREN: Implicit Neural Representations with Periodic Activation Functions [code]
  • arxiv2020 High Resolution Zero-Shot Domain Adaptation of Synthetically Rendered Face Images
  • arxiv2020 Structural-analogy from a Single Image Pair [code]
  • arxiv2020 Learning the Loss Functions in a Discriminative Space for Video Restoration