Shubham Tulsiani

Shubham Tulsiani - Home

I am an Assistant Professor at Carnegie Mellon University in the Robotics Institute, where I am a part of the Computer Vision group. I am interested in building perception systems that can infer the spatial and physical structure of the world they observe. Please see these recent talks for an overview. Prior to joining CMU, I was a Research Scientist at FAIR, Pittsburgh working with Abhinav Gupta. I previously graduated from UC, Berkeley where I was advised by Jitendra Malik, and also frequently collaborated with Alyosha Efros.

contact | google scholar | twitter

email: shubhtuls AT cmu.edu
Office: Smith Hall 213

Research Group

Our group is interested in inferring physically and spatially grounded representations from perceptual input, and leveraging these for advances in fundamental problems in computer vision and robot manipulation. We are always looking for strongly motivated PhD and MS students. If you are interested in joining our group, please read this. Dear Prospective Students, Thanks for the interest in being a part of our group! Unfortunately, I am unable to reply to individual emails, but hope you find the following helpful: I am a CMU student. How do I join your group? Send me an email and/or drop by my office - I'd be happy to chat! If you are an undergraduate, also consider reaching out to the PhD students in our group if their projects align with your interests. I want to join CMU. What graduate programs should I apply to? PhD. Applicants: While I am primarily affiliated with RI, I can supervise students admitted in any SCS department (e.g. MLD, CSD) so apply to the department that best matches your interests and background. If you are interested in working with me, mention this in your application statement. MS Applicants: RI offers MSR (research focused) and MSCV (industry focused) MS programs among others. Please apply to the program most aligned with your future goals. Should I contact you before applying to CMU for admission? Admissions across all PhD/MS programs are done by department-level committees and I am unable to help with individual applications. Please do feel free to reach out after you are admitted. Are you accepting interns/visitors? We do not have any short-term positions at this time.
PhD Students Hanzhe Hu Himangi Mittal Qitao Zhao Yehonathan Litman (co-advised with Fernando De la Torre) Yuxuan Kuang (co-advised with Katerina Fragkiadaki)

MS Students Clara Cong (MSCV) Lucas Wu (MSR) Minsik Jeon (MSR) Soumojit Bhattacharya (co-advised with Oliver Kroemer, MSR) Sungjae Park (MSR)


Alumni PhD: Jason Zhang (co-advised with Deva Ramanan), Sparse-view 3D in the Wild, 2024. Google Yufei Ye (co-advised with Abhinav Gupta), Learning to Perceive and Predict Everyday Interactions, 2024. Postdoc at Stanford Homanga Bharadhwaj (co-advised with Abhinav Gupta), Watch, Predict, Act: Robot Learning meets Web Videos, 2025. Meta MSR: Yanbo Xu. PhD at Princeton Bharath Raj. PhD at Cornell Zhizhuo (Z) Zhou. PhD at Stanford MSCV: Rena Ju, Poorvi Hebbar, Naveen Venkat, Mayank Agarwal, Yen-Chi Cheng, Paritosh Mittal Undergraduate: Amy Lin

Teaching

Publications (all | selected)

[New] DemoDiffusion: One-Shot Human Imitation using Pre-trained Diffusion Policy
Sungjae Park, Homanga Bharadhwaj, Shubham Tulsiani
ICRA, 2026
pdf project page bibtex code

[New] CRISP: Contact-Guided Real2Sim from Monocular Video with Planar Scene Primitives
Zihan Wang, Jiashun Wang, Jeff Tan, Yiwen Zhao, Jessica Hodgins, Shubham Tulsiani, Deva Ramanan
ICLR, 2026
pdf project page bibtex code

[New] Predicting 4D Hand Trajectory from Monocular Videos
Yufei Ye, Yao Feng, Omid Taheri, Haiwen Feng, Shubham Tulsiani, Michael J. Black
3DV, 2026
pdf project page bibtex code

[New] LightSwitch: Multi-view Relighting with Material-guided Diffusion
Yehonathan Litman, Fernando De la Torre, Shubham Tulsiani
ICCV, 2025
pdf project page bibtex code

[New] Gen2Act: Human Video Generation in Novel Scenarios enables Generalizable Robot Manipulation
Homanga Bharadhwaj, Debidatta Dwibedi, Abhinav Gupta, Shubham Tulsiani, Carl Doersch, Ted Xiao, Dhruv Shah, Fei Xia, Dorsa Sadigh, Sean Kirmani
CoRL, 2025
pdf project page bibtex

DiffusionSfM: Predicting Structure and Motion via Ray Origin and Endpoint Diffusion
Qitao Zhao, Amy Lin, Jeff Tan, Jason Y. Zhang, Deva Ramanan, Shubham Tulsiani
CVPR, 2025
pdf project page bibtex code

UniPhy: Learning a Unified Constitutive Model for Inverse Physics Simulation
Himangi Mittal, Peiye Zhuang, Hsin-Ying Lee, Shubham Tulsiani
CVPR, 2025
pdf project page bibtex code

AerialMegaDepth: Learning Aerial-Ground Reconstruction and View Synthesis
Khiem Vuong, Anurag Ghosh, Deva Ramanan*, Srinivasa Narasimhan*, Shubham Tulsiani*
CVPR, 2025
pdf project page bibtex code

Turbo3D: Ultra-fast Text-to-3D Generation
Hanzhe Hu, Tianwei Yin, Fujun Luan, Yiwei Hu, Hao Tan, Zexiang Xu, Sai Bi, Shubham Tulsiani*, Kai Zhang*
CVPR, 2025
pdf project page bibtex

SceneFactor: Factored Latent 3D Diffusion for Controllable 3D Scene Generation
Alexey Bokhovkin, Quan Meng, Shubham Tulsiani, Angela Dai
CVPR, 2025
pdf project page bibtex code

MaterialFusion: Enhancing Inverse Rendering with Material Diffusion Priors
Yehonathan Litman, Or Patashnik, Kangle Deng, Aviral Agrawal, Rushikesh Zawar, Fernando De la Torre, Shubham Tulsiani
3DV, 2025
pdf project page bibtex code

DressRecon: Freeform 4D Human Reconstruction from Monocular Video
Jeff Tan, Donglai Xiang, Shubham Tulsiani, Deva Ramanan, Gengshan Yang
3DV, 2025
pdf project page bibtex code

Sparse-view Pose Estimation and Reconstruction via Analysis by Generative Synthesis
Qitao Zhao, Shubham Tulsiani
NeurIPS, 2024
pdf project page bibtex code

Track2Act: Predicting Point Tracks from Internet Videos Enables Diverse Zero-shot Manipulation
Homanga Bharadhwaj, Roozbeh Mottaghi*, Abhinav Gupta*, Shubham Tulsiani*
ECCV, 2024
pdf project page bibtex code

UpFusion: Novel View Diffusion from Unposed Sparse View Observations
Bharath Raj Nagoor Kani, Hsin-Ying Lee, Sergey Tulyakov, Shubham Tulsiani
ECCV, 2024
pdf project page bibtex code

G-HOP: Generative Hand-Object Prior for Interaction Reconstruction and Grasp Synthesis
Yufei Ye, Abhinav Gupta, Kris Kitani, Shubham Tulsiani
CVPR, 2024
pdf project page bibtex code

MVD-Fusion: Single-view 3D via Depth-consistent Multi-view Generation
Hanzhe Hu*, Zhizhuo Zhou*, Varun Jampani, Shubham Tulsiani
CVPR, 2024
pdf project page bibtex code

Cameras as Rays: Pose Estimation via Ray Diffusion
Jason Y. Zhang*, Amy Lin*, Moneish Kumar, Tzu-Hsuan Yang, Deva Ramanan, Shubham Tulsiani
ICLR, 2024
pdf project page bibtex code

Towards Generalizable Zero-Shot Manipulation via Translating Human Interaction Plans
Homanga Bharadhwaj, Abhinav Gupta*, Vikash Kumar*, Shubham Tulsiani*
ICRA, 2024 (Finalist for Best Paper Award in Robot Manipulation)
pdf project page bibtex

RoboAgent: Towards Sample Efficient Robot Manipulation with Semantic Augmentations and Action Chunking
Homanga Bharadhwaj*, Jay Vakil*, Mohit Sharma*, Abhinav Gupta, Shubham Tulsiani, Vikash Kumar
ICRA, 2024
pdf project page bibtex data

RelPose++: Recovering 6D Poses from Sparse-view Observations
Amy Lin*, Jason Y. Zhang*, Deva Ramanan, Shubham Tulsiani
3DV, 2024
pdf project page bibtex code

Diffusion-Guided Reconstruction of Everyday Hand-Object Interaction Clips
Yufei Ye, Poorvi Hebbar, Abhinav Gupta, Shubham Tulsiani
ICCV, 2023
pdf project page bibtex code

Manipulate by Seeing: Creating Manipulation Controllers from Pre-Trained Representations
Jianren Wang*, Sudeep Dasari*, Mohan Kumar Srirama, Shubham Tulsiani, Abhinav Gupta
ICCV, 2023
pdf project page bibtex code

Mesh2Tex: Generating Mesh Textures from Image Queries
Alexey Bokhovkin, Shubham Tulsiani, Angela Dai
ICCV, 2023
pdf project page bibtex

Visual Affordance Prediction for Guiding Robot Exploration
Homanga Bharadhwaj, Abhinav Gupta, Shubham Tulsiani
ICRA, 2023
pdf project page bibtex code

Analogy-Forming Transformers for Few-Shot 3D Parsing
Nikolaos Gkanatsios*, Mayank Singh*, Zhaoyuan Fang, Shubham Tulsiani, Katerina Fragkiadaki
ICLR, 2023
pdf project page bibtex code

SparseFusion: Distilling View-conditioned Diffusion for 3D Reconstruction
Zhizhuo Zhou, Shubham Tulsiani
CVPR, 2023
pdf project page bibtex code

Affordance Diffusion: Synthesizing Hand-Object Interactions
Yufei Ye, Xueting Li, Abhinav Gupta, Shalini De Mello, Stan Birchfield, Jiaming Song, Shubham Tulsiani, Sifei Liu
CVPR, 2023
pdf project page bibtex

Monocular Dynamic View Synthesis: A Reality Check
Hang Gao, Ruilong Li, Shubham Tulsiani, Bryan Russell, Angjoo Kanazawa
NeurIPS, 2022
pdf project page bibtex code

RelPose: Predicting Probabilistic Relative Rotation for Single Objects in the Wild
Jason Y. Zhang, Deva Ramanan, Shubham Tulsiani
ECCV, 2022
pdf project page bibtex code

Pre-train, Self-train, Distill: A simple recipe for Supersizing 3D Reconstruction
Kalyan Vasudev Alwala, Abhinav Gupta, Shubham Tulsiani
CVPR, 2022
pdf project page bibtex code

What's in your hands? 3D Reconstruction of Generic Objects in Hands
Yufei Ye, Abhinav Gupta, Shubham Tulsiani
CVPR, 2022
pdf project page bibtex code

AutoSDF: Shape Priors for 3D Completion, Reconstruction and Generation
Paritosh Mittal*, Yen-Chi Cheng*, Maneesh Singh, Shubham Tulsiani
CVPR, 2022
pdf project page bibtex code

NeRS: Neural Reflectance Surfaces for Sparse-view 3D Reconstruction in the Wild
Jason Y. Zhang, Gengshan Yang, Shubham Tulsiani*, and Deva Ramanan*
NeurIPS, 2021
pdf project page bibtex video code

No RL, No Simulation: Learning to Navigate without Navigating
Meera Hahn, Devendra Chaplot, Shubham Tulsiani, Mustafa Mukadam, James M. Rehg, Abhinav Gupta
NeurIPS, 2021
pdf project page bibtex code

A Differentiable Recipe for Learning Visual Non-Prehensile Planar Manipulation
Bernardo Aceituno, Alberto Rodriguez, Shubham Tulsiani, Abhinav Gupta, Mustafa Mukadam
CoRL, 2021
pdf bibtex

Where2Act: From Pixels to Actions for Articulated 3D Objects
Kaichun Mo, Leonidas J. Guibas, Mustafa Mukadam, Abhinav Gupta, Shubham Tulsiani
ICCV, 2021
pdf bibtex code

PixelTransformer: Sample Conditioned Signal Generation
Shubham Tulsiani, Abhinav Gupta
ICML, 2021
pdf project page bibtex code

Shelf-Supervised Mesh Prediction in the Wild
Yufei Ye, Shubham Tulsiani, Abhinav Gupta
CVPR, 2021
pdf project page bibtex code

See, Hear, Explore: Curiosity via Audio-Visual Association
Victoria Dean, Shubham Tulsiani, Abhinav Gupta
NeurIPS, 2020
pdf project page bibtex video code

Visual Imitation Made Easy
Sarah Young, Dhiraj Gandhi, Shubham Tulsiani, Abhinav Gupta, Pieter Abbeel, Lerrel Pinto
CORL, 2020
pdf project page bibtex video code

Articulation-aware Canonical Surface Mapping
Nilesh Kulkarni, Abhinav Gupta, David Fouhey, Shubham Tulsiani
CVPR, 2020
pdf project page bibtex video code

Use the Force, Luke! Learning to Predict Physical Forces by Simulating Effects
Kiana Ehsani, Shubham Tulsiani, Saurabh Gupta, Ali Farhadi, Abhinav Gupta
CVPR, 2020
pdf project page bibtex code

Intrinsic Motivation for Encouraging Synergistic Behavior
Rohan Chitnis, Shubham Tulsiani, Saurabh Gupta, Abhinav Gupta
ICLR, 2020
pdf project page bibtex

Discovering Motor Programs by Recomposing Demonstrations
Tanmay Shankar, Shubham Tulsiani, Lerrel Pinto, Abhinav Gupta
ICLR, 2020
pdf bibtex

Efficient Bimanual Manipulation using Learned Task Schemas
Rohan Chitnis, Shubham Tulsiani, Saurabh Gupta, Abhinav Gupta
ICRA, 2020
preprint bibtex video

Object-centric Forward Modeling for Model Predictive Control
Yufei Ye, Dhiraj Gandhi, Abhinav Gupta, Shubham Tulsiani
CORL, 2019
pdf project page bibtex

Canonical Surface Mapping via Geometric Cycle Consistency
Nilesh Kulkarni, Abhinav Gupta*, Shubham Tulsiani*
ICCV, 2019
pdf project page bibtex video code

Compositional Video Prediction
Yufei Ye, Maneesh Singh, Abhinav Gupta*, Shubham Tulsiani*
ICCV, 2019
pdf project page bibtex code

3D-RelNet: Joint Object and Relational Network for 3D Prediction
Nilesh Kulkarni, Ishan Misra, Shubham Tulsiani, Abhinav Gupta
ICCV, 2019
pdf project page bibtex code

Order-Aware Generative Modeling Using the 3D-Craft Dataset
Zhuoyuan Chen*, Demi Guo*, Tong Xiao*, et. al.
ICCV, 2019
pdf bibtex

Learning Unsupervised Multi-View Stereopsis via Robust Photometric Consistency
Tejas Khot*, Shubham Agrawal*, Shubham Tulsiani, Christoph Mertz, Simon Lucey, Martial Hebert
arXiv preprint, 2019
pdf project page bibtex code

Layer-structured 3D Scene Inference via View Synthesis
Shubham Tulsiani, Richard Tucker, Noah Snavely
ECCV, 2018
pdf project page bibtex code

Learning Category-Specific Mesh Reconstruction from Image Collections
Angjoo Kanazawa*, Shubham Tulsiani*, Alexei A. Efros, Jitendra Malik
ECCV, 2018
pdf project page bibtex video code

Multi-view Consistency as Supervisory Signal for Learning Shape and Pose Prediction
Shubham Tulsiani, Alexei A. Efros, Jitendra Malik
CVPR, 2018
pdf project page bibtex code

Factoring Shape, Pose, and Layout from the 2D Image of a 3D Scene
Shubham Tulsiani, Saurabh Gupta, David Fouhey, Alexei A. Efros, Jitendra Malik
CVPR, 2018
pdf project page bibtex code

Hierarchical Surface Prediction for 3D Object Reconstruction
Christian Häne, Shubham Tulsiani, Jitendra Malik
3DV, 2017
pdf bibtex slides code

Learning Category-Specific Deformable 3D Models for Object Reconstruction
Shubham Tulsiani*, Abhishek Kar*, João Carreira, Jitendra Malik
TPAMI, 2016
pdf bibtex code

View Synthesis by Appearance Flow
Tinghui Zhou, Shubham Tulsiani, Weilun Sun, Jitendra Malik, Alexei A. Efros
ECCV, 2016
pdf bibtex code

Pose Induction for Novel Object Categories
Shubham Tulsiani, João Carreira, Jitendra Malik
ICCV, 2015
pdf bibtex code

Amodal Completion and Size Constancy in Natural Scenes
Abhishek Kar, Shubham Tulsiani, João Carreira, Jitendra Malik
ICCV, 2015
pdf bibtex

Viewpoints and Keypoints
Shubham Tulsiani, Jitendra Malik
CVPR, 2015
pdf bibtex code

Category-Specific Object Reconstruction from a Single Image
Abhishek Kar*, Shubham Tulsiani*, João Carreira, Jitendra Malik
CVPR, 2015 (Best Student Paper Award)
pdf project page bibtex code

Virtual View Networks for Object Reconstruction
João Carreira, Abhishek Kar, Shubham Tulsiani, Jitendra Malik
CVPR, 2015
pdf bibtex video code

A colorful approach to text processing by example
Kuat Yessenov, Shubham Tulsiani, Aditya Menon, Robert C Miller, Sumit Gulwani, Butler Lampson, Adam Kalai
UIST, 2013
pdf bibtex