윤제로의 제로베이스

https://openaccess.thecvf.com/content/CVPR2022/papers/Niemeyer_RegNeRF_Regularizing_Neural_Radiance_Fields_for_View_Synthesis_From_Sparse_CVPR_2022_paper.pdf https://m-niemeyer.github.io/regnerf RegNeRF NeRF optimizes the reconstruction loss for a given set of input images (blue cameras). For sparse inputs, however, this leads to degenerate solutions. In this work, we propose to sample unobserve..

https://arxiv.org/abs/2103.13415 Mip-NeRF: A Multiscale Representation for Anti-Aliasing Neural Radiance Fields The rendering procedure used by neural radiance fields (NeRF) samples a scene with a single ray per pixel and may therefore produce renderings that are excessively blurred or aliased when training or testing images observe scene content at different resolu arxiv.org https://github.com/..

https://arxiv.org/pdf/2107.02791.pdf https://github.com/dunbar12138/DSNeRF GitHub - dunbar12138/DSNeRF: Code release for DS-NeRF (Depth-supervised Neural Radiance Fields) Code release for DS-NeRF (Depth-supervised Neural Radiance Fields) - GitHub - dunbar12138/DSNeRF: Code release for DS-NeRF (Depth-supervised Neural Radiance Fields) github.com 기존의 pixelNeRF, MVSNeRF등 다양한 NeRF 논문들이 1장 혹은 적은 양의 i..

https://arxiv.org/abs/2211.13969 Unsupervised Continual Semantic Adaptation through Neural Rendering An increasing amount of applications rely on data-driven models that are deployed for perception tasks across a sequence of scenes. Due to the mismatch between training and deployment data, adapting the model on the new scenes is often crucial to obtain go arxiv.org NeRF 관련 되어서 arxiv를 항해하던 중 CVPR..

https://github.com/sxyu/pixel-nerf GitHub - sxyu/pixel-nerf: PixelNeRF Official Repository PixelNeRF Official Repository. Contribute to sxyu/pixel-nerf development by creating an account on GitHub. github.com http://arxiv.org/abs/2012.02190 pixelNeRF: Neural Radiance Fields from One or Few Images We propose pixelNeRF, a learning framework that predicts a continuous neural scene representation co..

Hu, Benran, et al. "Instance Neural Radiance Field." arXiv preprint arXiv:2304.04395 (2023). https://arxiv.org/pdf/2304.04395.pdf 이 논문은 그냥 arxiv를 떠다니다가 발견한 논문이다. indoor scene에 대해서 Instance level로 NeRF를 사용한 논문이다. 일종의 pipeline이라고 생각하면 될 듯 하다. Method 이 논문의 Instance-NeRF의 목적을 먼저 말하자면 3D scene에 모든 object를 detection bounding box, continuous 3D mask, 각각의 3D object의 class label까지 produce 위와 같은 목적을 갖고 있다..

https://fuxiao0719.github.io/projects/panopticnerf/ Panoptic NeRF: 3D-to-2D Label Transfer for Panoptic Urban Scene Segmentation Abstract Panoptic NeRF obtains per-pixel 2D semantic and instance labels from easy-to-obtain coarse 3D bounding primitives. --> Large-scale training data with high-quality annotations is critical for training semantic and instance segmentation models. Unfo fuxiao0719.g..

요즘 관심있는 분야는 Semantic Segmentation이다. 이 부분에 대해서 지식을 좀 쌓으려고 Segmentation 부분이랑 NeRF 부분을 공부해보려고 한다!! 그래서 공부한 것들을 좀 정리하려고 한다. 읽은 것들 Fu, Xiao, et al. "Panoptic nerf: 3d-to-2d label transfer for panoptic urban scene segmentation." arXiv preprint arXiv:2203.15224 (2022). Kundu, Abhijit, et al. "Panoptic neural fields: A semantic object-aware neural scene representation." Proceedings of the IEEE/CVF Conf..

Learning Object-Compositional Neural Radiance Field for Editable Scene Rendering(ICCV 2021) https://zju3dv.github.io/object_nerf/ Introduction 이 논문에서 추구하는 contribution은 다음과 같다. the first editable neural scene rendering system given a collection of posed images and 2D instance masks design a novel two-pathway architecture to learn object compositional neural radiance field the experiment and exte..

GNeRF: GAN-based Neural Radiance Field without Posed Camera(ICCV 2021) https://github.com/quan-meng/gnerf GitHub - quan-meng/gnerf: [ ICCV 2021 Oral ] Our method can estimate camera poses and neural radiance fields jointly when the ca [ ICCV 2021 Oral ] Our method can estimate camera poses and neural radiance fields jointly when the cameras are initialized at random poses in complex scenarios (o..