3D Computer Vision | Neural Field Representations

This is an add-on lecture to the CS4277/CS5477 - 3D Computer Vision course at the School of Computing at NUS. NeRF and Neural 3D reconstructions have recently become very popular and thus have to be included into the course. These are the links to the papers mentioned in this lecture: 1. Ben et al, NeRF: Representing Scenes as Neural Radiance Fields for View Synthesis, ECCV 2020 (https://arxiv.org/abs/2003.08934) 2. Tucker et al, Single-view view synthesis with multiplane images, CVPR 2020 (https://single-view-mpi.github.io/) 3. Li et al, MINE: Continuous-Depth MPI with Neural Radiance Fields, ICCV 2021 (https://vincentfung13.github.io/projects/mine/) 4, Wang et al, IBRNet: Learning Multi-View Image-Based Rendering, CVPR 2021 (https://arxiv.org/abs/2102.13090) 5. Yu et al, PlenOctrees for Real-time Rendering of Neural Radiance Fields, ICCV 2021 (https://alexyu.net/plenoctrees/) 6. Yu et al, Plenoxels: Radiance Fields without Neural Networks, CVPR 2022 (https://arxiv.org/abs/2112.05131) 7. Mueller et al, Instant Neural Graphics Primitives with a Multiresolution Hash Encoding, Siggraph 2022 (https://arxiv.org/abs/2201.05989) 8. Park et al, DeepSDF: Learning Continuous Signed Distance Functions for Shape Representation, CVPR 2019 9. Yariv et al, Volume Rendering of Neural Implicit Surfaces, NeurIPS 2021 (https://arxiv.org/abs/1901.05103) 10. Wang et al, NeuS: Learning Neural Implicit Surfaces by Volume Rendering for Multi-view Reconstruction, NeurIPS 2021 (https://arxiv.org/abs/2106.10689) 11. Lin et al, BARF: Bundle-Adjusting Neural Radiance Fields, ICCV 2021 (https://arxiv.org/abs/2104.06405) 12. Peng, et al, Animatable Neural Radiance Fields for Modeling Dynamic Human Bodies, ICCV 2021 (https://zju3dv.github.io/animatable_nerf/) 13. Chen et al, SNARF: Differentiable Forward Skinning for Animating Non-Rigid Neural Implicit Shapes, ICCV 2021 (https://arxiv.org/abs/2104.03953) 14. Kwon et al, Neural Human Performer: Learning Generalizable Radiance Fields for Human Performance Rendering, NeurIPS 2021 (https://arxiv.org/abs/2109.07448) I also briefly mentioned these papers: 1. Yu et al, pixelNeRF: Neural Radiance Fields from One or Few Images, CVPR 2021 (https://alexyu.net/pixelnerf/) 2. Oechsle et al, UNISURF: Unifying Neural Implicit Surfaces and Radiance Fields for Multi-View Reconstruction, ICCV 2021 (https://moechsle.github.io/unisurf/) 3. Yariv et al, IDR: Multiview Neural Surface Reconstruction by Disentangling Geometry and Appearance, NeurIPS 2020 (https://lioryariv.github.io/idr/) Here's the papers related to Neural Field Representation published by my group at NUS: 1. Chen and Lee, DBARF: Deep Bundle-Adjusting Generalizable Neural Radiance Field , CVPR 2023. (https://aibluefisher.github.io/dbarf/) 2. Yang et al, ContraNeRF: Generalizable Neural Radiance Fields for Synthetic-to-Real Novel View Synthesis via Contrastive Learning , CVPR 2023. (https://arxiv.org/abs/2303.11052) 3. Yan et al, NeRF-DS: Neural Radiance Fields for Dynamic Specular Objects , CVPR 2023. (https://jokeryan.github.io/projects/nerf-ds/) 4. Low and Lee, Minimal Neural Atlas: Parameterizing Complex Surfaces with Minimal Charts and Distortion, ECCV 2022. (https://github.com/low5545/minimal-neural-atlas) 5. Li et al, MINE: Continuous-Depth MPI with Neural Radiance Fields, ICCV 2021 (https://vincentfung13.github.io/projects/mine/) 6. Guo et al, Incremental Learning for Neural Radiance Field with Uncertainty-Filtered Knowledge Distillation, In arXiv, 2023 (https://arxiv.org/abs/2212.10950) 7. Yan et al, OD-NeRF: Efficient Training of On-the-Fly Dynamic Neural Radiance Fields, In arXiv, 2023 (https://arxiv.org/abs/2305.14831) Lecturer: Gim Hee Lee (https://www.comp.nus.edu.sg/~leegh/) Follow on Twitter: https://twitter.com/gimhee_lee Disclaimer: This video lecture is provided freely for your reference. The lecturer and NUS are not responsible for anything expressed herein.