윤제로의 제로베이스

Paper Reading 본문

Self Paper-Seminar

Paper Reading

윤_제로 2023. 1. 11. 17:22

이번 겨울 방학 때 읽고 싶은 논문들,,, 2달 밖에 시간이 없어서 빠듯하게 하루에 한편 목표로 잡아도,,, 50개는 읽을까 싶지만

하루에 한편씩 Rough하게 읽는 게 목표

 

출처 : https://github.com/MatrixBrain/awesome-NeRF

 

GitHub - MatrixBrain/awesome-NeRF: A curated list of awesome neural radiance fields (NeRF) papers.

A curated list of awesome neural radiance fields (NeRF) papers. - GitHub - MatrixBrain/awesome-NeRF: A curated list of awesome neural radiance fields (NeRF) papers.

github.com

그리고 머리에 남기고 싶은 내용 

https://media-ai.tistory.com/7

 

논문 읽기와 ML/DL 커리어 경력에 대한 조언 by 앤드류 응

이번 포스팅은 medium 사이트에 있는 포스팅을 번역한 글입니다! 우리 모두의 ML/DL 선생님이신 앤드류응 교수님께서 스탠포트 CS 230 강의에서 ML/DL 커리어와 논문 읽기에 대한 강의를 하신 것을 정

media-ai.tistory.com

2023-1 NeRF

NeRF

Data Augemntation

  • GeoAug: Data Augmentation for Few-Shot NeRF with Geometry Constrains - ECCV(2022)
  • Neural-Sim: Learning to generate Training Data wiht NeRF - ECCV(2022) / 2023.01.13
  • Aug-NeRF: Training Stronger Neural Radiance Fields wiht Triple-Level Physically-Grounded Augmentations - CVPR(2022)

Few Shot

  • D^2NeRF: Self-Supervised Desoupling of dynamic and Static objects from a Monocular Video - NeurIPS(2022)
  • ActiveNeRF: Learning where to See with Uncertainty Estimation - ECCV(2022)
  • SinNeRF: Training Neural Radinace Fields on Complex Scenes from a Single Input Views - CVPR(2022)
  • Dense Depth Prirors for Neural Radiance Fields from Sparse Input Views - CVPR(2022)
  • RegNeRF: Regularizing Neural Radiance Fields for View Synthesis from Sparse Inputs - CVPR(2022)
  • AutoRF: Learning 3D Object Radiance Fields from Single View Observation - CVPR(2022)
  • InfoNeRF: Ray Entropy Minimization for Few-Shot Neural Volume Rendering - CVPR(2022)
  • Depth-supervised NeRF: Fewer Views and Faster Training for Free - CVPR(2022)
  • Putting NeRF on a Diet: Semantically Consistent Few-Shot View Synthesis - ICCV(2021)
  • Neural Radiance Flow for 4D View Synthesis and Video Processing - ICCV(2021)
  • MVSNeRF: Fast Generalizable Radiance Field Reconstruction from Multi-View Stereo - ICCV(2021)
  • pixelNeRF: Neural Radiance Fields from One or Few Images - CVPR(2021)

Rendering Performance

  • MobileNeRF: Exploiting the Polygon Rasterization Pipeline for Efficient Neural Field Rendering on Mobile Architectures - arXiv(2022)
  • Compressible-composable NeRF via Rank-residual Decomposition - NeurIPS(2022)
  • TensoRF: Tensorial Radiance Fields - NeurIPS(2022)
  • NeXT: Towards High Quality Neural Radiance Fields via Multi-Skip Transformer - ECCV(2022)
  • R2L: Distilling Neural Radiance Field to Neural Light Field for Efficient Novel View Synthesis - ECCV(2022)
  • Gaussian Activated Neural Radiance Fields for High Fidelity Reconstruction & Pose Estimation - ECCV(2022)
  • Conditional-Flow NeRF: Accurate 3D Modelling with Reliable Uncertainty Quantification - ECCV(2022)
  • ViewFormer: NeRF-free Neural Rendering from Few Images Using Transformers - ECCV(2022)
  • Gaussian Activated Neural Radiance Fields for High Fidelity Reconstruction & Pose Estimation - ECCV(2022)
  • Ref-NeRF: Structured View-Dependent Appearance for Neural Radiance Fields - CVPR(2022)
  • Urban Radiance Fields - CVPR(2022)
  • GeoNeRF: Generalizing NeRF with Geometry Priors - CVPR(2022)
  • NeRFReN: Neural Radiance Fields with Reflections - CVPR(2022)
  • GNeRF: GAN-based Neural Radiance Field without Posed Camera - ICCV(2021)
  • UNISURF: Unifying Neural Implicit Surfaces and Radiance Fields for Multi-View Reconstruction - ICCV(2021)
  • MINE: Towards Continuous Depth MPI with NeRF for Novel View Synthesis - ICCV(2021)
  • Nerfies: Deformable Neural Radiance Fields - ICCV(2021)

Training & Inference Efficiency

  • Instant Neural Graphics Primitives with a Multiresolution Hash Encoding - ACM TOG(2022)
  • Geometry-Guided Progressive NeRF for Generalizable and Efficient Neural Human Rendering - ECCV(2022)
  • ViewFormer: NeRF-free Neural Rendering from Few Images Using Transformers - ECCV(2022)
  • AdaNeRF: Adaptive Sampling for Real-time Rendering of Neural Radiance Fields - ECCV(2022)
  • Point-NeRF: Point-based Neural Radiance Fields - CVPR(2022) / 2023.01.12
  • DIVeR: Real-time and Accurate Neural Radiance Fields with Deterministic Integration for Volume Rendering - CVPR(2022)
  • Fourier PlenOctrees for Dynamic Radiance Field Rendering in Real-time - CVPR(2022)
  • Direct Voxel Grid Optimization: Super-fast Convergence for Radiance Fields Reconstruction - CVPR(2022)
  • EfficientNeRF – Efficient Neural Radiance Fields - CVPR(2022)
  • Mip-NeRF 360: Unbounded Anti-Aliased Neural Radiance Fields - CVPR(2022)
  • Mip-NeRF: A Multiscale Representation for Anti-Aliasing Neural Radiance Fields - ICCV(2021)
  • PlenOctrees for Real-time Rendering of Neural Radiance Fields - ICCV(2021)
  • KiloNeRF: Speeding up Neural Radiance Fields with Thousands of Tiny MLPs - ICCV(2021)
  • Baking Neural Radiance Fields for Real-Time View Synthesis - ICCV(2021)
  • DeRF: Decomposed Radiance Fields - CVPR(2021)

NeRF Related Task

Deblur & Denoise

  • Deblur-NeRF: Neural Radiance Fields from Blurry Images - CVPR(2022)
  • NAN: Noise-Aware NeRFs for Burst-Denoising - CVPR(2022)
  • NeRF in the Dark: High Dynamic Range View Synthesis from Noisy Raw Images - CVPR(2022)

Depth Estimation

  • AR-NeRF: Unsupervised Learning of Depth and Defocus Effects from Natural Images with Aperture Rendering Neural Radiance Fields - CVPR(2022)
  • NerfingMVS: Guided Optimization of Neural Radiance Fields for Indoor Multi-view Stereo - ICCV(2021)

High Dynamic Range(HDR)

  • HDR-Plenoxels: Self-Calibrating High Dynamic Range Radiance Fields - ECCV(2022)
  • HDR-NeRF: High Dynamic Range Neural Radiance Fields - CVPR(2022)

Large Scale Scene

  • NeRF for Outdoor Scene Relighting - ECCV(2022)
  • NeRFusion: Fusing Radiance Fields for Large-Scale Scene Reconstruction - CVPR(2022)
  • Mega-NeRF: Scalable Construction of Large-Scale NeRFs for Virtual Fly-Throughs - CVPR(2022)
  • Block-NeRF: Scalable Large Scene Neural View Synthesis - CVPR(2022)
  • Hallucinated Neural Radiance Fields in the Wild - CVPR(2022)
  • Unconstrained Scene Generation with Locally Conditioned Radiance Fields - ICCV(2021)
  • NeRF in the Wild: Neural Radiance Fields for Unconstrained Photo Collections - CVPR(2021)

Pose Misalignment

  • BARF: Bundle-Adjusting Neural Radiance Fields - ICCV(2021)

Reinforcement Learning

  • Reinforcement Learning with Neural Radiance Fields - NeurIPS(2022)

Relighting

  • NeRF for Outdoor Scene Relighting - ECCV(2022)
  • Factorized and Controllable Neural Re-Rendering of Outdoor Scene for Photo Extrapolation - ACM MM(2022)
  • NeRD: Neural Reflectance Decomposition from Image Collections - CVPR(2021)
  • NeRV: Neural Reflectance and Visibility Fields for Relighting and View Synthesis - CVPR(2021)
  • NeRFactor: Neural Factorization of Shape and Reflectance Under an Unknown Illumination - ACM TOG(2021)

Segmentation

  • Decomposing NeRF for Editing via Feature Field Distillation - NeurIPS(2022)
  • LaTeRF: Label and Text Driven Object Radiance Fields - ECCV(2022)

Stylized

  • ARF: Artistic Radiance fields - ECCV(2022)
  • StylizedNeRF: Consistent 3D Scene Stylization as Stylized NeRF via 2D-3D Mutual Learning - CVPR(2022)
  • Learning to Stylize Novel Views - ICCV(2021)

Surface Reconstruction

  • UNISURF: Unifying Neural Implicit Surfaces and Radiance Fields for Multi-View Reconstruction - ICCV(2021)
  • NeuS: Learning Neural Implicit Surfaces by Volume Rendering for Multi-view Reconstruction - NeurIPS(2021)
  • Volume Rendering of Neural Implicit Surfaces - NeurIPS(2021)

View Synthesis Exrapolation

  • Ray Priors through Reprojection: Improving Neural Radiance Fields for Novel View Extrapolation - CVPR(2022)

++++

  • Neural Volumetric Object Selection - CVPR(2022)
  • CodeNeRF: Disentangled Neural Radiance Fields for Object Categories - ICCV(2021)
  • Self-Calibrating Neural Radiance Fields - ICCV(2021)

'Self Paper-Seminar' 카테고리의 다른 글

CVPR 2023 paper 동향  (0) 2023.08.31
어텐션 이해하기... 2편  (0) 2023.06.10
어텐션 이해하기...  (0) 2023.05.22
2022 IROS 내 맘대로 Paper List - 2탄  (0) 2023.02.28
2022 IROS 내 맘대로 Paper List - 1탄  (0) 2023.02.17