Shubham Tulsiani

@inproceedings{zhao2025diffusionsfm,
 title={DiffusionSfM: Predicting Structure and Motion via Ray Origin and Endpoint Diffusion}, 
 author={Qitao Zhao and Amy Lin and Jeff Tan and Jason Y. Zhang and Deva Ramanan and Shubham Tulsiani},
 booktitle={CVPR},
 year={2025} 
}

@inproceedings{mittal2025uniphy,
 title={UniPhy: Learning a Unified Constitutive Model for Inverse Physics Simulation},
 author={Mittal, Himangi and Zhuang, Peiye and Lee, Hsin-Ying and Tulsiani, Shubham},
 booktitle={CVPR},
 year={2025} 
}

@inproceedings{vuong2025aerialmegadepth,
 title={AerialMegaDepth: Learning Aerial-Ground Reconstruction and View Synthesis},
 author={Vuong, Khiem and Ghosh, Anurag and Ramanan, Deva and Narasimhan, Srinivasa and Tulsiani, Shubham},
 booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
 year={2025},
}

@inproceedings{huturbo3d,
 title={Turbo3D: Ultra-fast Text-to-3D Generation},
 author={Hanzhe Hu and Tianwei Yin and Fujun Luan and Yiwei Hu and Hao Tan and Zexiang Xu and Sai Bi and Shubham Tulsiani and Kai Zhang},
 booktitle={CVPR},
 year={2025} 
}

@inproceedings{bokhovkin2025scenefactor,
 title={SceneFactor: Factored Latent 3D Diffusion for Controllable 3D Scene Generation}, 
 author={Bokhovkin, Alexey and Meng, Quan and Tulsiani, Shubham and Dai, Angela},
 booktitle={CVPR},
 year={2025} 
}

@inproceedings{litman2025materialfusion,
 author = {Yehonathan Litman and Or Patashnik and Kangle Deng and Aviral Agrawal and Rushikesh Zawar and Fernando De la Torre and Shubham Tulsiani},
 title = {MaterialFusion: Enhancing Inverse Rendering with Material Diffusion Priors},
 booktitle = {3DV},
 year = {2025}
}

@inproceedings{tan2024dressrecon,
 title={DressRecon: Freeform 4D Human Reconstruction from Monocular Video},
 author={Tan, Jeff and Xiang, Donglai and Tulsiani, Shubham and Ramanan, Deva and Yang, Gengshan},
 booktitle = {3DV},
 year = {2025}
}

@inproceedings{bharadhwaj2024track2act,
 author = {Homanga Bharadhwaj and Roozbeh Mottaghi and Abhinav Gupta and Shubham Tulsiani},
 title = {Track2Act: Predicting Point Tracks from Internet Videos enables Diverse Zero-shot Robot Manipulation},
 booktitle={European Conference on Computer Vision (ECCV)},
 year = {2024}
}

@inproceedings{bharadhwaj2024track2act,
 author = {Homanga Bharadhwaj and Roozbeh Mottaghi and Abhinav Gupta and Shubham Tulsiani},
 title = {Track2Act: Predicting Point Tracks from Internet Videos enables Diverse Zero-shot Robot Manipulation},
 booktitle={European Conference on Computer Vision (ECCV)},
 year = {2024}
}

@inproceedings{kani24upfusion,
 author = {Nagoor Kani, Bharath Raj and Lee, Hsin-Ying and Tulyakov, Sergey and Tulsiani, Shubham},
 title = {UpFusion: Novel View Diffusion from Unposed Sparse View Observations},
 booktitle={European Conference on Computer Vision (ECCV)},
 year = {2024}
}

@inproceedings{ye2024ghop,
 author = {Ye, Yufei and Gupta, Abhinav and Kitani, Kris and Tulsiani, Shubham}
 title = {G-HOP: Generative Hand-Object Prior for Interaction Reconstruction and Grasp Synthesis},
 booktitle={CVPR},
 year={2024}
}

@inproceedings{hu2024mvdfusion,
 title={MVD-Fusion: Single-view 3D via Depth-consistent Multi-view Generation}, 
 author={Hanzhe Hu and Zhizhuo Zhou and Varun Jampani and Shubham Tulsiani},
 booktitle={CVPR},
 year={2024}
}

@InProceedings{zhang2024raydiffusion,
 title={Cameras as Rays: Pose Estimation via Ray Diffusion},
 author={Zhang, Jason Y and Lin, Amy and Kumar, Moneish and Yang, Tzu-Hsuan and Ramanan, Deva and Tulsiani, Shubham},
 booktitle={International Conference on Learning Representations (ICLR)},
 year={2024}
}

@article{bharadhwaj2023towards,
 title={Towards Generalizable Zero-Shot Manipulation via Translating Human Interaction Plans},
 author={Bharadhwaj, Homanga and Gupta, Abhinav and Kumar, Vikash and Tulsiani, Shubham},
 journal={arXiv preprint arXiv:2312.00775},
 year={2023}
}

@article{bharadhwaj2023roboagent,
 title={Roboagent: Generalization and efficiency in robot manipulation via semantic augmentations and action chunking},
 author={Bharadhwaj, Homanga and Vakil, Jay and Sharma, Mohit and Gupta, Abhinav and Tulsiani, Shubham and Kumar, Vikash},
 journal={arXiv preprint arXiv:2309.01918},
 year={2023}
}

@inproceedings{lin2024relposepp,
 title={RelPose++: Recovering 6D Poses from Sparse-view Observations},
 author={Lin, Amy and Zhang, Jason Y and Ramanan, Deva and Tulsiani, Shubham},
 booktitle={3DV},
 year={2024}
}

@inproceedings{ye2023vhoi,
 author = {Ye, Yufei and Hebbar, Poorvi and Gupta, Abhinav and Tulsiani, Shubham}
 title = {Diffusion-Guided Reconstruction of Everyday Hand-Object Interaction Clips},
 booktitle = {ICCV},
 year = {2023}
}

@article{wang2023manipulate,
 title={Manipulate by Seeing: Creating Manipulation Controllers from Pre-Trained Representations},
 author={Wang, Jianren and Dasari, Sudeep and Srirama, Mohan Kumar and Tulsiani, Shubham and Gupta, Abhinav},
 booktitle={International Conference on Computer Vision (ICCV)},
 year={2023}
}

@inproceedings{ye2023vhoi,
 title = {Mesh2Tex: Generating Mesh Textures from Image Queries},
 author = {Bokhovkin, Alexey and Tulsiani, Shubham and Dai, Angela},
 booktitle = {ICCV},
 year = {2023}
}

@article{BharadhwajVisual,	
 Author = {Homanga Bharadhwaj and Abhinav Gupta and Shubham Tulsiani},	
 Journal={IEEE International Conference on Robotics and Automation (ICRA)},	
 Year = {2023},	
 Title = {Visual Affordance Prediction for Guiding Robot Exploration}	
}

@article{gkanatsios2023analogical,
 author = {Gkanatsios, Nikolaos and Singh, Mayank and Fang, Zhaoyuan and Tulsiani, Shubham and Fragkiadaki, Katerina},
 title = {Analogy-Forming Transformers for Few-Shot 3D Parsing},
 journal = {ICLR},
 year = {2023},
}

@inproceedings{zhou2023sparsefusion,
 title={SparseFusion: Distilling View-conditioned Diffusion for 3D Reconstruction}, 
 author={Zhizhuo Zhou and Shubham Tulsiani},
 booktitle={CVPR},
 year={2023}
}

@inproceedings{ye2023affordance,
 title={Affordance Diffusion: Synthesizing Hand-Object Interactions}, 
 author={Yufei Ye and Xueting Li and Abhinav Gupta and Shalini De Mello and Stan Birchfield, Jiaming Song and Shubham Tulsiani and Sifei Liu},
 booktitle={CVPR},
 year={2023}
}

@inproceedings{gao2022dynamic,
 title={Monocular Dynamic View Synthesis: A Reality Check},
 author={Gao, Hang and 
 Li, Ruilong and 
 Tulsiani, Shubham and 
 Russell, Bryan and 
 Kanazawa, Angjoo},
 booktitle={NeurIPS},
 year={2022},
}

@InProceedings{zhang2022relpose,
 title = {{RelPose}: Predicting Probabilistic Relative Rotation for Single Objects in the Wild},
 author = {Zhang, Jason Y. and Ramanan, Deva and Tulsiani, Shubham},
 booktitle = {European Conference on Computer Vision},
 year = {2022}
}

@inProceedings{vasudev2022ss3d,
 title={Pre-train, Self-train, Distill: A simple recipe for Supersizing 3D Reconstruction},
 author={Alwala, Kalyan Vasudev and Gupta, Abhinav and Tulsiani, Shubham},
 year={2022},
 booktitle={Computer Vision and Pattern Recognition (CVPR)}
}

@inProceedings{ye2022ihoi,
 title={What's in your hands? 3D Reconstruction of Generic Objects in Hands},
 author={Ye, Yufei and Gupta, Abhinav and Tulsiani, Shubham},
 year={2022},
 booktitle={Computer Vision and Pattern Recognition (CVPR)}
}

@inproceedings{autosdf2022,
 title={{AutoSDF}: Shape Priors for 3D Completion, Reconstruction and Generation},
 author={Mittal, Paritosh and Cheng, Yen-Chi and Singh, Maneesh and Tulsiani, Shubham},
 booktitle={CVPR},
 year={2022}
}

@inproceedings{zhang2021ners,
 title={{NeRS}: Neural Reflectance Surfaces for Sparse-view 3D Reconstruction in the Wild},
 author={Zhang, Jason Y. and Yang, Gengshan and Tulsiani, Shubham and Ramanan, Deva},
 booktitle={Conference on Neural Information Processing Systems},
 year={2021}
}

@article{hahn2021nrns,
 title={No RL, No Simulation: Learning to Navigate without Navigating},
 author={Meera Hahn and Devendra Chaplot and Shubham Tulsiani and Mustafa Mukadam and James Rehg and Abhinav Gupta},
 booktitle={Neural Information Processing Systems},
 year={2021},
}

@inProceedings{aceituno21planar,
 title={A Differentiable Recipe for Learning Visual Non-Prehensile Planar Manipulation},
 author={Aceituno, Bernardo and Rodriguez, Alberto and Tulsiani, Shubham and Gupta, Abhinav and Mukadam, Mustafa},
 year={2021},
 booktitle={Conference on Robot Learning (CoRL)}
}

@inProceedings{mo2021where2act,
 title={Where2Act: From Pixels to Actions for Articulated 3D Objects},
 author={Mo, Kaichun and Guibas, Leonidas and Mukadam, Mustafa and Gupta, Abhinav and Tulsiani, Shubham},
 year={2021},
 booktitle={International Conference on Computer Vision (ICCV)}
}

@inProceedings{tulsiani2021pixel,
 title={PixelTransformer: Sample Conditioned Signal Generation},
 author={Tulsiani, Shubham and Gupta, Abhinav},
 year={2021},
 booktitle={International Conference on Machine Learning (ICML)}
}

@inProceedings{ye2021shelf,
 title={Shelf-Supervised Mesh Prediction in the Wild},
 author={Ye, Yufei and Tulsiani, Shubham and Gupta, Abhinav},
 year={2021},
 booktitle={Computer Vision and Pattern Recognition (CVPR)}
}

@article{dean2020see,
 title={See, hear, explore: Curiosity via audio-visual association},
 author={Dean, Victoria and Tulsiani, Shubham and Gupta, Abhinav},
 journal={Advances in Neural Information Processing Systems},
 volume={33},
 year={2020}
}

@inProceedings{young2020vime,
 title={Visual Imitation Made Easy},
 author={Young, Sarah and Gandhi, Dhiraj and Tulsiani, Shubham and Gupta, Abhinav and Abbeel, Pieter and Pinto, Lerrel},
 year={2020},
 booktitle={Conference on Robot Learning (CORL)}
}

@inProceedings{kulkarni2020acsm,
 title={Articulation-aware Canonical Surface Mapping},
 author={Kulkarni, Nilesh and Gupta, Abhinav and Fouhey, David and Tulsiani, Shubham},
 year={2020},
 booktitle={Computer Vision and Pattern Recognition (CVPR)}
}

@inProceedings{ehsani2020force,
 title={Use the Force, Luke! Learning to Predict Physical Forces by Simulating Effects},
 author={Ehsani, Kiana and Tulsiani, Shubham and Gupta, Saurabh and Farhadi, Ali and Gupta, Abhinav},
 year={2020},
 booktitle={Computer Vision and Pattern Recognition (CVPR)}
}

@inproceedings{chitnis20synergy,
 title={Intrinsic Motivation for Encouraging Synergistic Behavior},
 author={Chitnis, Rohan and Tulsiani, Shubham and Gupta, Saurabh and Gupta, Abhinav},
 booktitle={ICLR},
 year={2020}
}

@inproceedings{shankar20motor,
 title={Discovering Motor Programs by Recomposing Demonstrations},
 author={Shankar, Tanmay and Tulsiani, Shubham and Pinto, Lerrel and Gupta, Abhinav},
 booktitle={ICLR},
 year={2020}
}

@inproceedings{chitnis20schema,
 title={Efficient Bimanual Manipulation Using Learned Task Schemas},
 author={Chitnis, Rohan and Tulsiani, Shubham and Gupta, Saurabh and Gupta, Abhinav},
 booktitle={ICRA},
 year={2020}
}

@inProceedings{ye2019ocm,
 title={Object-centric Forward Modeling for Model Predictive Control},
 author={Ye, Yufei and Gandhi, Dhiraj and Gupta, Abhinav and Tulsiani, Shubham},
 year={2019},
 booktitle={Conference on Robot Learning (CORL)}
}

@inProceedings{kulkarni2019csm,
 title={Canonical Surface Mapping via Geometric Cycle Consistency},
 author={Kulkarni, Nilesh and Gupta, Abhinav and Tulsiani, Shubham},
 year={2019},
 booktitle={International Conference on Computer Vision (ICCV)}
}

@inProceedings{ye2019cvp,
 title={Compositional Video Prediction},
 author={Ye, Yufei and Singh, Maneesh and Gupta, Abhinav and Tulsiani, Shubham},
 year={2019},
 booktitle={International Conference on Computer Vision (ICCV)}
}

@inProceedings{kulkarni2019relnet,
 title={3D-RelNet: Joint Object and Relational Network for 3D Prediction},
 author={Nilesh Kulkarni, Ishan Misra, Shubham Tulsiani, Abhinav Gupta},
 booktitle={ICCV},
 year={2019}
}

@inProceedings{chen2019craft,
 title={Order-Aware Generative Modeling Using the 3D-Craft Dataset},
 author={Zhuoyuan Chen, Demi Guo, Tong Xiao, Saining Xie, Xinlei Chen, Haonan Yu, Jonathan Gray, Kavya Srinet, Haoqi Fan, Jerry Ma, Charles R. Qi, Shubham Tulsiani, Arthur Szlam, and C. Lawrence Zitnick},
 booktitle={ICCV},
 year={2019}
}

@article{khot2019learning,
 title={Learning Unsupervised Multi-View Stereopsis via Robust Photometric Consistency},
 author={Khot, Tejas and Agrawal, Shubham and Tulsiani, Shubham and Mertz, Christoph and Lucey, Simon and Hebert, Martial},
 journal={arXiv preprint arXiv:1905.02706},
 year={2019}
}

@inProceedings{lsiTulsiani18,
 title={Layer-structured 3D Scene Inference via View Synthesis},
 author = {Shubham Tulsiani
 and Richard Tucker
 and Noah Snavely},
 booktitle={ECCV},
 year={2018}
}

@inProceedings{cmrKanazawa18,
 title={Learning Category-Specific Mesh Reconstruction
 from Image Collections},
 author = {Angjoo Kanazawa and
 Shubham Tulsiani
 and Alexei A. Efros
 and Jitendra Malik},
 booktitle={ECCV},
 year={2018}
}

@inProceedings{mvcTulsiani18,
 title={Multi-view Consistency as Supervisory Signal
 for Learning Shape and Pose Prediction},
 author = {Shubham Tulsiani
 and Alexei A. Efros
 and Jitendra Malik},
 booktitle={Computer Vision and Pattern Recognition (CVPR)},
 year={2018}
}

@inProceedings{factored3dTulsiani17,
 title={Factoring Shape, Pose, and Layout from the 2D Image of a 3D Scene},
 author = {Shubham Tulsiani
 and Saurabh Gupta
 and David Fouhey
 and Alexei A. Efros
 and Jitendra Malik},
 booktitle={Computer Vision and Pattern Recognition (CVPR)},
 year={2018}
}

@inProceedings{drcTulsiani17,
 title={Multi-view Supervision for Single-view Reconstruction
 via Differentiable Ray Consistency},
 author = {Shubham Tulsiani
 and Tinghui Zhou
 and Alexei A. Efros
 and Jitendra Malik},
 booktitle={Computer Vision and Pattern Recognition (CVPR)},
 year={2017}
}

@inProceedings{abstractionTulsiani17,
 title={Learning Shape Abstractions by Assembling Volumetric Primitives},
 author = {Shubham Tulsiani
 and Hao Su
 and Leonidas J. Guibas
 and Alexei A. Efros
 and Jitendra Malik},
 booktitle={Computer Vision and Pattern Recognition (CVPR)},
 year={2017}
}

@incollection{hspHane17,
 author = {Christian H{\"a}ne and
 Shubham Tulsiani and
 Jitendra Malik},
 title = {Hierarchical Surface Prediction for 3D Object Reconstruction},
 booktitle = {arXiv preprint arXiv:1704.00710},
 year = {2017}
}

@article{pamishapeTulsianiKCM15,
 author = {Shubham Tulsiani and
 Abhishek Kar and
 Jo{\~{a}}o Carreira and
 Jitendra Malik},
 title = {Learning Category-Specific Deformable 3D
 Models for Object Reconstruction},
 journal = {TPAMI},
 year = {2016},
}

@incollection{appFlowZhou16,
author = {Tinghui Zhou and
Shubham Tulsiani and
Weilun Sun and
Jitendra Malik and
Alexei A. Efros},
title = {View Synthesis by Appearance Flow},
booktitle = {ECCV},
year = {2016}
}

@inProceedings{poseInductionTCM15,
 author = {Shubham Tulsiani and
 Jo{\~{a}}o Carreira and
 Jitendra Malik},
 title = {Pose Induction for Novel Object Categories},
 year={2015},
 booktitle={International Conference on Computer Vision (ICCV)}
}

@inProceedings{amodalKTCM15,
 author = {Abhishek Kar and
 Shubham Tulsiani and
 Jo{\~{a}}o Carreira and
 Jitendra Malik},
 title = {Amodal Completion and Size Constancy in Natural Scenes},
 year={2015},
 booktitle={International Conference on Computer Vision (ICCV)}
 }

@inProceedings{vpsKpsTulsianiM15,
 author = {Shubham Tulsiani and Jitendra Malik},
 title = {Viewpoints and Keypoints},
 year={2015},
 booktitle={Computer Vision and Pattern Recognition (CVPR)}
}

@inProceedings{shapesKarTCM15,
 author = {Abhishek Kar and
 Shubham Tulsiani and
 Jo{\~{a}}o Carreira and
 Jitendra Malik},
 title = {Category-Specific Object Reconstruction from a Single Image},
 year={2015},
 booktitle={Computer Vision and Pattern Recognition (CVPR)}
}

@inProceedings{vvnCarreiraKTM15,
 author = {Jo{\~{a}}o Carreira and
 Abhishek Kar and
 Shubham Tulsiani and
 Jitendra Malik},
 title = {Virtual View Networks for Object Reconstruction},
 year={2015},
 booktitle={Computer Vision and Pattern Recognition (CVPR)}
}

@inproceedings{yessenov2013colorful,
 title={A colorful approach to text processing by example},
 author={Yessenov, Kuat and
 Tulsiani, Shubham and
 Menon, Aditya and
 Miller, Robert C and
 Gulwani,Sumit and
 Lampson, Butler and
 Kalai, Adam},
 booktitle={UIST},
 pages={495--504},
 year={2013},
 organization={ACM}
}