Merge pull request awesome-NeRF#99 from lhy0807/main

Add two robotics works
chensiyuan030105 · Aug 16, 2022 · 9fc6bc2 · 9fc6bc2
2 parents 8f5a361 + cc313f1
commit 9fc6bc2
Show file tree

Hide file tree

Showing 3 changed files with 31 additions and 3 deletions.
diff --git a/README.md b/README.md
@@ -22,7 +22,7 @@ A curated list of awesome neural radiance fields papers, inspired by [awesome-co
 - [DeRF: Decomposed Radiance Fields](https://arxiv.org/abs/2011.12490), Rebain et al. Arxiv 2020 | [bibtex](./NeRF-and-Beyond.bib#L222-L228) <!---Rebain20arxiv_derf-->
 - [DONeRF: Towards Real-Time Rendering of Compact Neural Radiance Fields using Depth Oracle Networks](https://depthoraclenerf.github.io/), Neff et al., CGF 2021 | [bibtex](./citations/donerf.txt) <!---neff2021donerf-->
 - [FastNeRF: High-Fidelity Neural Rendering at 200FPS](https://arxiv.org/abs/2103.10380), Garbin et al., Arxiv 2021 | [bibtex](./citations/fastnerf.txt) <!---Garbin21arxiv_FastNeRF-->
-- [KiloNeRF: Speeding up Neural Radiance Fields with Thousands of Tiny MLPs ](https://arxiv.org/abs/2103.13744), Reiser et al., Arxiv 2021 | [github](https://github.com/creiser/kilonerf) | [bibtex](./citations/kilonerf.txt) <!---reiser2021kilonerf-->
+- [KiloNeRF: Speeding up Neural Radiance Fields with Thousands of Tiny MLPs ](https://arxiv.org/abs/2103.13744), Reiser et al., ICCV 2021 | [github](https://github.com/creiser/kilonerf) | [bibtex](./citations/kilonerf.txt) <!---reiser2021kilonerf-->
 - [PlenOctrees for Real-time Rendering of Neural Radiance Fields](https://alexyu.net/plenoctrees/), Yu et al., Arxiv 2021 | [github](https://github.com/sxyu/volrend) | [bibtex](./citations/plenoctrees.txt) <!---yu2021plenoctrees-->
 - [Mixture of Volumetric Primitives for Efficient Neural Rendering](https://arxiv.org/abs/2103.01954), Lombardi et al., SIGGRAPH 2021 | [bibtex](./citations/mixture.txt)
 - [Light Field Networks: Neural Scene Representations with Single-Evaluation Rendering](https://vsitzmann.github.io/lfns/), Sitzmann et al., Arxiv 2021 | [bibtex](./citations/lfn.txt)
@@ -68,7 +68,7 @@ A curated list of awesome neural radiance fields papers, inspired by [awesome-co
 - [CAMPARI: Camera-Aware Decomposed Generative Neural Radiance Fields](https://arxiv.org/pdf/2103.17269.pdf), Niemeyer & Geiger, Arxiv 2021 | [bibtex](./citations/CAMPARI.txt)
 - [NeRF-VAE: A Geometry Aware 3D Scene Generative Model](https://arxiv.org/pdf/2104.00587.pdf), Kosiorek et al., Arxiv 2021 | [bibtex](./citations/nerf-vae.txt)
 - [Unconstrained Scene Generation with Locally Conditioned Radiance Fields](https://apple.github.io/ml-gsn/), DeVries et al., Arxiv 2021 | [bibtex](./citations/gsn.txt)
-- [MVSNeRF: Fast Generalizable Radiance Field Reconstruction from Multi-View Stereo](https://apchenstu.github.io/mvsnerf/), Chen et al., Arxiv 2021 | [github](https://github.com/apchenstu/mvsnerf) | [bibtex](https://github.com/yenchenlin/awesome-NeRF/blob/main/citations/mvsnerf.txt)
+- [MVSNeRF: Fast Generalizable Radiance Field Reconstruction from Multi-View Stereo](https://apchenstu.github.io/mvsnerf/), Chen et al., ICCV 2021 | [github](https://github.com/apchenstu/mvsnerf) | [bibtex](https://github.com/yenchenlin/awesome-NeRF/blob/main/citations/mvsnerf.txt)
 - [Stereo Radiance Fields (SRF): Learning View Synthesis from Sparse Views of Novel Scenes](https://virtualhumans.mpi-inf.mpg.de/srf/), Chibane et al., CVPR 2021 | [bibtex](./citations/srf.txt)
 - [Neural Rays for Occlusion-aware Image-based Rendering](https://liuyuan-pal.github.io/NeuRay/), Liu et al., Arxiv 2021 | [bibtex](./citations/neuray.txt)
 - [Putting NeRF on a Diet: Semantically Consistent Few-Shot View Synthesis](https://www.ajayj.com/dietnerf), Matthew Tancik et al., Arxiv 2021 | [bibtex](./citations/DietNeRF.txt)
@@ -82,7 +82,7 @@ A curated list of awesome neural radiance fields papers, inspired by [awesome-co
 - [iNeRF: Inverting Neural Radiance Fields for Pose Estimation](http://yenchenlin.me/inerf/), Yen-Chen et al. IROS 2021 | [bibtex](./NeRF-and-Beyond.bib#L321-L327) <!---YenChen20arxiv_iNeRF-->
 - [A-NeRF: Surface-free Human 3D Pose Refinement via Neural Rendering](https://lemonatsu.github.io/ANeRF-Surface-free-Pose-Refinement/), Su et al. Arxiv 2021 | [bibtex](./citations/a-nerf.txt) <!---Su21arxiv_A_NeRF-->
 - [NeRF--: Neural Radiance Fields Without Known Camera Parameters](http://nerfmm.active.vision/), Wang et al., Arxiv 2021 | [github](https://github.com/ActiveVisionLab/nerfmm) | [bibtex](./citations/nerf--.txt) <!---Wang21arxiv_nerfmm-->
-- [iMAP: Implicit Mapping and Positioning in Real-Time](https://edgarsucar.github.io/iMAP/), Sucar et al., Arxiv 2021 | [bibtex](./citations/imap.txt)
+- [iMAP: Implicit Mapping and Positioning in Real-Time](https://edgarsucar.github.io/iMAP/), Sucar et al., ICCV 2021 | [bibtex](./citations/imap.txt)
 - [NICE-SLAM: Neural Implicit Scalable Encoding for SLAM](https://pengsongyou.github.io/nice-slam), Zhu et al., Arxiv 2021 | [bibtex](./citations/nice-slam.txt)
 - [GNeRF: GAN-based Neural Radiance Field without Posed Camera](https://arxiv.org/abs/2103.15606), Meng et al., Arxiv 2021 | [bibtex](https://github.com/yenchenlin/awesome-NeRF/blob/main/citations/gnerf.txt)
 - [BARF: Bundle-Adjusting Neural Radiance Fields](https://chenhsuanlin.bitbucket.io/bundle-adjusting-NeRF/), Lin et al., ICCV 2021 | [bibtex](./citations/barf.txt)
@@ -125,6 +125,10 @@ A curated list of awesome neural radiance fields papers, inspired by [awesome-co
 #### Depth Estimation
 - [NerfingMVS: Guided Optimization of Neural Radiance Fields for Indoor Multi-view Stereo](https://weiyithu.github.io/NerfingMVS/), Wei et al., ICCV 2021 | [bibtex](./citations/NerfingMVS.txt)
 
+#### Robotics
+- [3D Neural Scene Representations for Visuomotor Control](https://3d-representation-learning.github.io/nerf-dy/), Li et al., CoRL 2021 Oral | [bibtex](./citations/nerf-dy.txt)
+- [Vision-Only Robot Navigation in a Neural Radiance World](https://arxiv.org/abs/2110.00168), Adamkiewicz et al., RA-L 2022 Vol.7 No.2 | [bibtex](./citations/vision-only.txt)
+
 ## Talks
 - [NeRF: Representing Scenes as Neural Radiance Fields for View Synthesis](https://www.youtube.com/watch?v=LCTYRqW-ne8&t=10190s), Ben Mildenhall
 - [Understanding and Extending Neural Radiance Fields](https://www.youtube.com/watch?v=nRyOzHpcr4Q&feature=emb_logo&ab_channel=cvprtum), Barron et al.

diff --git a/citations/nerf-dy.txt b/citations/nerf-dy.txt
@@ -0,0 +1,15 @@
+@InProceedings{pmlr-v164-li22a,
+  title = 	 {3D Neural Scene Representations for Visuomotor Control},
+  author =       {Li, Yunzhu and Li, Shuang and Sitzmann, Vincent and Agrawal, Pulkit and Torralba, Antonio},
+  booktitle = 	 {Proceedings of the 5th Conference on Robot Learning},
+  pages = 	 {112--123},
+  year = 	 {2022},
+  editor = 	 {Faust, Aleksandra and Hsu, David and Neumann, Gerhard},
+  volume = 	 {164},
+  series = 	 {Proceedings of Machine Learning Research},
+  month = 	 {08--11 Nov},
+  publisher =    {PMLR},
+  pdf = 	 {https://proceedings.mlr.press/v164/li22a/li22a.pdf},
+  url = 	 {https://proceedings.mlr.press/v164/li22a.html},
+  abstract = 	 {Humans have a strong intuitive understanding of the 3D environment around us. The mental model of the physics in our brain applies to objects of different materials and enables us to perform a wide range of manipulation tasks that are far beyond the reach of current robots. In this work, we desire to learn models for dynamic 3D scenes purely from 2D visual observations. Our model combines Neural Radiance Fields (NeRF) and time contrastive learning with an autoencoding framework, which learns viewpoint-invariant 3D-aware scene representations. We show that a dynamics model, constructed over the learned representation space, enables visuomotor control for challenging manipulation tasks involving both rigid bodies and fluids, where the target is specified in a viewpoint different from what the robot operates on. When coupled with an auto-decoding framework, it can even support goal specification from camera viewpoints that are outside the training distribution. We further demonstrate the richness of the learned 3D dynamics model by performing future prediction and novel view synthesis. Finally, we provide detailed ablation studies regarding different system designs and qualitative analysis of the learned representations.}
+}
diff --git a/citations/vision-only.txt b/citations/vision-only.txt
@@ -0,0 +1,9 @@
+@ARTICLE{9712211,  
+author={Adamkiewicz, Michal and Chen, Timothy and Caccavale, Adam and Gardner, Rachel and Culbertson, Preston and Bohg, Jeannette and Schwager, Mac},  
+journal={IEEE Robotics and Automation Letters},   
+title={Vision-Only Robot Navigation in a Neural Radiance World},   
+year={2022}, 
+volume={7},  
+number={2},  
+pages={4606-4613},  
+doi={10.1109/LRA.2022.3150497}}