Skip to content

Latest commit

 

History

History

07

Folders and files

NameName
Last commit message
Last commit date

parent directory

..
summary
summary
 
 
README.md
README.md
 
 

README.md

2021 July

Full List of papers - updated weekly

  • Baking Neural Radiance Fields for Real-Time View Synthesis (진오)
  • NeRF: Representation Scenes as Neural Radiance Fields for View synthesis (민국)
  • A Random CNN Sees Objects: One Inductive Bias of CNN and Its Applications (우현)
  • PixelNerf: Neural Radiance Fields from One or Few Images (민국)
  • Hypercorrelation Squeeze for Few-Shot Segmentation (승욱)
  • Dense Contrastive Learning for Self-Supervised Visual Pre-Training (우현)
  • Unsupervised Learning of Dense Visual Representations (우현)
  • Neural Reprojection Error: Merging Feature Learning and Camera Pose Estimation (승욱)
  • Few-shot Image Generation via Cross-domain Correspondence (우현)
  • EfficientDet: Scalable and Efficient Object Detection (승욱)
  • Depth-supervised NeRF: Fewer Views and Faster Training for Free (진오)
  • Occupancy Networks - Learning 3D Reconstruction in Function Space (진오)
  • Rethinking and Improving the Robustness of Image Style Transfer (우현, 승욱)
  • RepVGG: Making VGG-style ConvNets Great Again (승욱)
  • ViTGAN: Training GANs with Vision Transformers (민국)
  • GIRAFFE: Representing Scene As Compositional Generative Nerual Feature Fields (윤우, 민국, 수현)
  • kiloNeRF ([윤우]](./summary/17.md))
  • TransGAN: Two Pure Transformers Can Make One strong GAN, and That Can Scale Up (민국)
  • Per-Pixel Classification is Not All You Need for Semantic Segmentation (우현)
  • Residual Network Behave like ensembles of Relatively Shallow Networks (승욱)
  • D-NeRF: Neural Radiance Fields for Dynamic Scenes (진오)
  • SOE-Net: A Self-Attention and Orientation Encoding Network for Point Cloud based Place Recognition (승욱)
  • MCL-GAN: Generative Adversarial Networks with Multiple Specialized Discriminators (우현)
  • NeRF--: Neural Radiance Fields Without Known Camera Parameters (진오)
  • Stereo radiance fields ([윤우]](./summary/26.md))
  • Weakly-supervised physically Unconstrained Gaze Estimation (승욱)
  • Convolutional Occupancy Networks (윤우)
  • Generative Multi-Adversarial Networks (우현)
  • GRAF: Generative Radiance Fields for 3D-Aware Image Synthesis (민국, 진오)
  • Editing Conditional Radiance Fields (진오, 민국)
  • Swapping Autoencoder for Deep Image Manipulation (우현)
  • divco diverse conditional image synthesis via contrastive generative adversarial network (민국)
  • Robust Neural Routing Through Space Partitions for Camera Relocalization in Dynamic Indoor Environments (강희)
  • ChannelPruning for Accelerating Very Deep Neural Networks (승욱)
  • CorrNet3D : Unsupervised End-to-end Learning of Dense Correspondence for 3D point clouds (강희)
  • On the Continuity Rotation Representations in Neural Networks (윤우)
  • Anycost GANs for Interactive Image Synthesis and Editing (우현)
  • Indoor Visual Localization with Dense Mathing and View Synthesis (강희)
  • NERF Research Directions (윤우)
  • Taming Transformers for High-Resolution Image Synthesis (우현)
  • ShaRF: Shape-conditioned Radiance Fiedls from a Single View (진오)
  • Learning Deep Features for Discriminative Localization (승욱)
  • cGANs with Auxiliary Discriminative Classifier (민국)
  • Nerfies: Deformable Nerual Radiance Fields (진오)
  • Correlated Input-Dependent Label Noise in Large-scale Image Classification (승욱)
  • Playable Video Generation (우현)
  • Few-shot Image Generation via Cross-domain Correspondence (우현)
  • A Simple Framework for Contrastive Learning of Visual Representations (수현)
  • On Buggy Resizing Libraries and Surprising Subtleties in FID Calculation (민국)
  • MinkLoc++ : Lidar and Monocular Image Fusion for Place Recognition (강희)
  • KeypointDeformer: Unsupervised 3D Keypoint DIscovery for Shape Control (승욱)
  • High-Fidelity Neural Human Motion Transfer from Monocular Video (우현)
  • Big self-supervised Models are Strong Semi-supervised learners (수현)
  • NeuralRecon: Real-Time Coherent 3D Reconstruction From Monocular Video (우현)
  • Quantifying Attention Flow in Transformers (승욱)
  • Repurposing GANs for One-Shot Semantic Part Segmentation (우현, 민국)
  • PIC-NET : Point Cloud and Image Collaboration Network for Large-Scale Place Recognition (강희)
  • Training Generative Adversarial Networks in One Stage (민국)
  • Transformer Interpretability Beyond Attention Visualization (승욱)
  • GNeRF: GAN-based Neural Radiance Field without Posed Camera (진오)
  • Exploring Simple Siamese Representation Learning (수현)
  • Generic Attention-model Explainability for Interpreting Bi-Modal and Encoder-Decoder Transformers (승욱)
  • Nex: Real-time View Synthesis with Neural Basis Expansion (우현)