Dynamo-Depth: Fixing Unsupervised Depth Estimation for Dynamical Scenes
Yihong Sun, Bharath Hariharan
In NeurIPS, 2023
TLDR : We improve unsupervised monocular depth estimation for dynamical scenes by modeling 3D independent flow and motion segmentation.
pdf bibtex
```
@inproceedings{Yihong2023Dynamo,
title = {Dynamo-Depth: Fixing Unsupervised Depth Estimation for Dynamical Scenes},
author = {Yihong Sun and  Bharath Hariharan},
year = {2023},
booktitle = {NeurIPS}
}
```
Tracking Everything Everywhere All at Once
Qianqian Wang, Yen-Yu Chang, Ruojin Cai, Zhengqi Li, Bharath Hariharan, Aleksander Holynski, Noah Snavely
In ICCV, 2023 (Oral)[Best student paper]
TLDR : A neural field approach to estimating long-term correspondences even through occlusions
pdf bibtex
```
@inproceedings{Wang2023Tracking,
title = {Tracking Everything Everywhere All at Once},
author = {Qianqian Wang and  Yen-Yu Chang and  Ruojin Cai and  Zhengqi Li and  Bharath Hariharan and  Aleksander Holynski and  Noah Snavely},
year = {2023},
booktitle = {ICCV}
}
```
Doppelgangers: Learning to Disambiguate Images of Similar Structures
Ruojin Cai, Joseph Tung, Qianqian Wang, Hadar Averbuch-Elor, Bharath Hariharan, Noah Snavely
In ICCV, 2023 (Oral)
TLDR : We learn to classify whether an image pair in an SfM pipeline captures the same structure, or similar but distinct structures
pdf bibtex
```
@inproceedings{Cai2023Doppelgangers,
title = {Doppelgangers: Learning to Disambiguate Images of Similar Structures},
author = {Ruojin Cai and  Joseph Tung and  Qianqian Wang and  Hadar Averbuch-Elor and  Bharath Hariharan and  Noah Snavely},
year = {2023},
booktitle = {ICCV}
}
```
Polynomial Neural Fields for Subband Decomposition and Manipulation
Guandao Yang*, Sagie Benaim*, Varun Jampani, Kyle Genova, Jonathan T. Barron, Thomas Funkhouser, Bharath Hariharan, Serge Belongie
In NeurIPS, 2022
TLDR : A new architecture for neural fields that explicitly decomposes signals into Fourier and other bases
pdf bibtex
```
@inproceedings{Yang2022Polynomial,
title = {Polynomial Neural Fields for Subband Decomposition and Manipulation},
author = {Guandao Yang and  Sagie Benaim and  Varun Jampani and  Kyle Genova and  Jonathan T. Barron and  Thomas Funkhouser and  Bharath Hariharan and  Serge Belongie},
year = {2022},
booktitle = {NeurIPS}
}
```

Geometry Processing using Neural Fields
Guandao Yang, Serge Belongie, Bharath Hariharan, Vladlen Koltun
In NeurIPS, 2021
TLDR : Can we manipulate shapes by solely manipulating a neural implicit field?
pdf bibtex

@inproceedings{Yang2021Geometry,
title = {Geometry Processing using Neural Fields},
author = {Guandao Yang and  Serge Belongie and  Bharath Hariharan and  Vladlen Koltun},
year = {2021},
booktitle = {NeurIPS}
}

Extreme Rotation Estimation using Dense Correlation Volumes
Ruojin Cai, Hadar Averbuch-Elor, Bharath Hariharan, Noah Snavely
In CVPR, 2021
TLDR : Can we estimate relative camera pose between two views which don't overlap at all?
pdf project page bibtex
```
@inproceedings{Cai2021Extreme,
title = {Extreme Rotation Estimation using Dense Correlation Volumes},
author = {Ruojin Cai and  Hadar Averbuch-Elor and  Bharath Hariharan and  Noah Snavely},
year = {2021},
booktitle = {CVPR}
}
```
Stay Positive: Non-Negative Image Synthesis for Augmented Reality
Katie Luo, Guandao Yang, Wenqi Xian, Harald Haraldsson, Bharath Hariharan, Serge Belongie
In CVPR, 2021 (Oral)
TLDR : How do we project a synthetic world into a real one by only adding light?
pdf project page bibtex
```
@inproceedings{Luo2021Stay,
title = {Stay Positive: Non-Negative Image Synthesis for Augmented Reality},
author = {Katie Luo and  Guandao Yang and  Wenqi Xian and  Harald Haraldsson and  Bharath Hariharan and  Serge Belongie},
year = {2021},
booktitle = {CVPR}
}
```
Wasserstein Distances for Stereo Depth Estimation
Divyansh Garg, Yan Wang, Bharath Hariharan, Mark Campbell, Kilian Q Weinberger, Wei-Lun Chao
In NeurIPS, 2020 (Oral)
TLDR : A new loss function for depth estimation that compares distributions of predicted depth with the ground truth
pdf project page bibtex
```
@inproceedings{Garg2020Wasserstein,
title = {Wasserstein Distances for Stereo Depth Estimation},
author = {Divyansh Garg and  Yan Wang and  Bharath Hariharan and  Mark Campbell and  Kilian Q Weinberger and  Wei-Lun Chao},
year = {2020},
booktitle = {NeurIPS}
}
```
Learning Gradient Fields for Shape Generation
Ruojin Cai, Guandao Yang, Hadar Averbuch-Elor, Zekun Hao, Serge Belongie, Noah Snavely, Bharath Hariharan
In ECCV, 2020 (Spotlight)
TLDR : A new way of representing shapes by using neural networks to model the gradient of the probability distribution of surface points.
pdf project page bibtex
```
@inproceedings{Cai2020Learning,
title = {Learning Gradient Fields for Shape Generation},
author = {Ruojin Cai and  Guandao Yang and  Hadar Averbuch-Elor and  Zekun Hao and  Serge Belongie and  Noah Snavely and  Bharath Hariharan},
year = {2020},
booktitle = {ECCV}
}
```
Learning Feature Descriptors using Camera Pose Supervision
Qianqian Wang, Xiaowei Zhou, Bharath Hariharan, Noah Snavely
In ECCV, 2020 (Oral)
TLDR : We learn neural network-based feature descriptors solely from camera pose without any ground truth correspondences
pdf supp project page bibtex
```
@inproceedings{Wang2020Learning,
title = {Learning Feature Descriptors using Camera Pose Supervision},
author = {Qianqian Wang and  Xiaowei Zhou and  Bharath Hariharan and  Noah Snavely},
year = {2020},
booktitle = {ECCV}
}
```
PointFlow: 3D Point Cloud Generation with Continuous Normalizing Flows
Guandao Yang*, Xun Huang*, Zekun Hao, Ming-Yu Liu, Serge Belongie, Bharath Hariharan
In ICCV, 2019 (Oral)
TLDR : We consider point clouds as distributions of surface points, which we model using a variant of neural ODEs
pdf project page bibtex
```
@inproceedings{Yang2019PointFlow,
title = {PointFlow: 3D Point Cloud Generation with Continuous Normalizing Flows},
author = {Guandao Yang and  Xun Huang and  Zekun Hao and  Ming-Yu Liu and  Serge Belongie and  Bharath Hariharan},
year = {2019},
booktitle = {ICCV}
}
```
Few-Shot Generalization for Single-Image 3D Reconstruction via Prior
Bram Wallace, Bharath Hariharan
In ICCV, 2019
TLDR : A single-view 3D reconstruction system that explicitly leverages the average category shape, and can thus generalize to new classes without training
pdf bibtex
```
@inproceedings{Wallace2019Few-shot,
title = {Few-Shot Generalization for Single-Image 3D Reconstruction via Prior},
author = {Bram Wallace and  Bharath Hariharan},
year = {2019},
booktitle = {ICCV}
}
```
Learning Single-View 3D Reconstruction with Limited Pose Supervision
Guandao Yang, Yin Cui, Serge Belongie, Bharath Hariharan
In ECCV, 2018
TLDR : We explore many ways of reducing the need for ground truth annotations for training 3D reconstruction systems
pdf bibtex
```
@inproceedings{Yang2018Learning,
title = {Learning Single-View 3D Reconstruction with Limited Pose Supervision},
author = {Guandao Yang and  Yin Cui and  Serge Belongie and  Bharath Hariharan},
year = {2018},
booktitle = {ECCV}
}
```

Publications