I am a Professor at the CSE Department of UCSD. I work on computer vision, machine learning and computer graphics, with applications in autonomous driving, robotics and augmented reality.
An LLM agent for visual program synthesis trainable with reinforced self-training using just weak supervision from vision-language tasks.
LidaRF: Delving into Lidar for Neural Radiance Field on Street Scenes Shanlin Sun, Bingbing Zhuang, Ziyu Jiang, Buyu Liu, Xiaohui Xie, Manmohan Chandraker
A Lidar-enhanced neural radiance field to transform drive videos into photorealistic sensor simulation testbeds.
TextureDreamer: Image-guided Texture Synthesis through Geometry-aware Diffusion Yu-Ying Yeh, Jia-Bin Huang, Changil Kim, Lei Xiao, Thu Nguyen-Phuoc, Numair Khan, Cheng Zhang, Manmohan Chandraker, Carl S Marshall, Zhao Dong, Zhengqin Li
Transfer photorealistic, high-fidelity and geometry-aware textures from 3-5 images to arbitrary 3D meshes.
AIDE: An Automatic Data Engine for Object Detection in Autonomous Driving Mingfu Liang, Jong-Chyi Su, Samuel Schulter, Sparsh Garg, Shiyu Zhao, Ying Wu, Manmohan Chandraker
A VLM and LLM-based framework for issue-finding, auto-labeling, continual training and automated verification for visual perception in autonomous driving.
What You See Is What You GAN: Rendering Every Pixel for High-Fidelity Geometry in 3D GANs Alex Trevithick, Matthew Chan, Towaki Takikawa, Umar Iqbal, Shalini De Mello, Manmohan Chandraker, Ravi Ramamoorthi, Koki Nagano
Question decomposition that allows multi-billion scale vision-language models to approach reasoning-heavy visual question-answering as a two-step rather than a single-step problem.
NeurOCS: Neural NOCS Supervision for Monocular 3D Object Localization Zhixiang Min, Bingbing Zhuang, Samuel Schulter, Buyu Liu, Enrique Dunn, Manmohan Chandraker
Learn dense 3D object shapes for autonomous driving, using differentiable rendering with instance masks and 3D boxes, along with category-level priors.
A flow-free and single-shot prediction approach for video frame interpolation, allowing efficient ultra-slow motion effects using just 3D convolutions.
Factorized Inverse Path Tracing for Efficient and Accurate Material-Lighting Estimation Liwen Wu, Rui Zhu, Mustafa B. Yaldiz, Yinhao Zhu, Hong Cai, Janarbek Matai, Fatih Porikli, Tzu-Mao Li, Manmohan Chandraker, Ravi Ramamoorthi
Joint estimation of emitters and materials in inverse rendering, to enable high-quality AR applications like scene relighting and object insertion.
Q: How to Specialize Large VLMs to Data-Scarce VQA? A: Train on Unlabeled Images! Zaid Khan, Vijay Kumar, Samuel Schulter, Raymond Fu, Manmohan Chandraker
Pseudo-label question-answers in unlabeled images, for fine-tuning an existing large vision-language model on visual question answering in a data-scarce target dataset.
A Theory of Topological Derivatives for Inverse Rendering of Geometry Ishit Mehta, Manmohan Chandraker, Ravi Ramamoorthi
Inverse rendering through variational optimization of image functionals that allows for discrete topology changes by nucleating hole or phase changes, with applications to multiview 3D reconstruction and text-to-image generation.
Physically-Based Editing of Indoor Scene Lighting from a Single Image Zhengqin Li, Jia Shi, Sai Bi, Rui Zhu, Kalyan Sunkavalli, Milos Hasan, Zexiang Xu, Ravi Ramamoorthi, Manmohan Chandraker
Estimation of visible and invisible light sources from a single image of an indoor scene, to enable scene relighting and object insertion with full global effects.
A Level Set Theory for Neural Implicit Evolution under Explicit Flows Ishit Mehta, Manmohan Chandraker, Ravi Ramamoorthi
An open source dataset of indoor scenes with high-quality tools and ground truth for shape, material and lighting, for augmented reality and robotics applications.
Divide-and-Conquer for Lane-Aware Diverse Trajectory Prediction
Sriram Narayanan, Ramin Moslemi, Francesco Pittaluga, Buyu Liu, Manmohan Chandraker
An instance-affinity based criterion with a multi-sample contrastive loss for improved domain alignment.
Neural Mesh Flow: 3D Manifold Mesh Generation via Diffeomorphic Flows Kunal Gupta, Manmohan Chandraker NeurIPS 2020 [PDF]
Neural ODEs to generate 3D meshes with guaranteed manifoldness, enabling physically meaningful applications like rendering, simulations and 3D printing.
A physically-motivated network for joint shape and material estimation, as well as relighting under novel illumination conditions, using a single image captured by a mobile phone camera.
Constant-time, scene consistent and diverse trajectory prediction regardless of number of agents, along with a dynamics simulator that diversifies top-views of real scenes.
Single-View Metrology in the Wild Rui Zhu, Xingyi Wang, Yannick Hold-Geoffroy, Federico Perazzi, Jonathan Eisenmann, Kalyan Sunkavalli, Manmohan Chandraker ECCV 2020 [PDF]
Recover object height and camera parameters from a single unconstrained image, through a network that imbibes weakly supervised geometric constraints through bounding boxes and the horizon.
Through the Looking Glass: Neural 3D Reconstruction of Transparent Shapes Zhengqin Li, Yu-Ying Yeh, Manmohan Chandraker CVPR 2020 (Oral) [PDF]
A physically-motivated network that models refractions and reflections to recover high-quality 3D geometry for complex transparent shapes using as few as 5-12 natural images.
Inverse Rendering for Complex Indoor Scenes: Shape, Spatially-Varying Lighting and SVBRDF from a Single Image Zhengqin Li, Mohammad Shafiei, Ravi Ramamoorthi, Kalyan Sunkavalli, Manmohan Chandraker CVPR 2020 (Oral) [PDF]
A physically-motivated network that recovers shape, complex material and spatially varying lighting from a single mobile phone image to enable photorealistic indoor AR applications.
Peek-a-Boo: Occlusion Reasoning in Indoor Scenes with Plane Representations Ziyu Jiang, Buyu Liu, Samuel Schulter, Zhangyang Wang, Manmohan Chandraker CVPR 2020 (Oral) [PDF]
A novel planar representation for indoor 3D scene understanding that reasons about occlusions, with new metrics and a new dataset.
Universal Semi-Supervised Semantic Segmentation T. Kalluri, G. Varma, M.K. Chandraker and C.V. Jawahar ICCV 2019[PDF]
Learning fair representations that perform well across both data-rich and data-poor domains, applied to semantic segmentation that minimizes annotation and deployment costs.
A Parametric Top-View Representation of Complex Road Scenes Z. Wang, B. Liu, S. Schulter and M.K. Chandraker CVPR 2019 [PDF]
A parametric representation for 3D scene understanding of complex road scenes that is intuitive for human visualization and interpretable for higher-level decision making.
Learning Structure-And-Motion-Aware Rolling Shutter Correction B. Zhuang, Q.-H. Tran, P. Ji, L.F. Cheong and M.K. Chandraker CVPR 2019 (Oral) [PDF]
Theoretical limits on SFM with a rolling-shutter camera and leveraging data-driven priors through a network that learns camera motion and scene stucture to undistort a single rolling shutter image.
Joint Pixel and Feature-Level Domain Adaptation for Recognition in the Wild L. Tran, K. Sohn, X. Yu, X. Liu, and M.K. Chandraker CVPR 2019 [PDF][Supplementary]
Unsupervised domain adaptation that combines insights from semi-supervised learning for feature-level adaptation and 3D geometry-guided image synthesis for pixel-level adaptation.
Learning to Simulate N. Ruiz, S. Schulter and M.K. Chandraker ICLR 2019 [PDF]
A reinforcement learning-based method for automatically adjusting the parameters of any non-differentiable simulator, thereby controlling the distribution of synthesized data in order to maximize the accuracy of a model trained on that data.
Unsupervised Domain Adaptation for Distance Metric Learning K. Sohn, W. Shang, X. Yu and M.K. Chandraker ICLR 2019 [PDF]
Making face recognition fair across ethnicities through unsupervised adaptation across domains with non-overlapping label spaces, retaining identification power on all ethnicities while keeping representations for all identities well-separated.
Single-Shot Analysis of Refractive Shapes Using Convolutional Neural Networks J. Stets, Z. Li, J. Frisvad and M.K. Chandraker WACV 2019 [PDF]
Single-image depth map and normal estimation for transparent shapes using a network trained on a new synthetic dataset.
AutoNUE: A Dataset for Exploring Problems of Autonomous Navigation in Unconstrained Environments G. Varma, A. Subramanian, A. Namboodiri, M.K. Chandraker and C.V. Jawahar WACV 2019 [PDF]
Taking a step towards self-driving on Indian roads through a novel large-scale dataset that provides instance segmentation and object detection labels.
Learning to Reconstruct Shape and Spatially-Varying Reflectance with a Single Image Z. Li, Z. Xu, R. Ramamoorthi, K. Sunkavalli and M.K. Chandraker SIGGRAPH Asia 2018 [PDF]
A differential rendering layer with global illumination to train a network that recovers shape and complex, spatially-varying material using a single image acquired with a mobile phone camera.
Materials for Masses: SVBRDF Acquisition with a Single Mobile Phone Image Z. Li, K. Sunkavalli and M.K. Chandraker ECCV 2018 (Oral) [PDF]
A differentiable rendering layer that models image formation with a complex spatially-varying BRDF to recover high-quality material information using a single mobile phone image.
Learning to Look around Objects for Top-View Representations of Outdoor Scenes S. Schulter, M. Zhai, N. Jacobs and M.K. Chandraker ECCV 2018 [PDF]
Predict occluded portions of the scene layout by looking around foreground objects like cars or pedestrians, with learned priors and rules about typical road layouts from simulated or, if available, map data.
Learning to Adapt Structured Output Space for Semantic Segmentation Y.-H. Tsai, W.-C. Hung, S. Schulter, K. Sohn, M.-H. Yang and M.K. Chandraker CVPR 2018 (Spotlight) [PDF]
Unsupervised domain adaptation for semantic segmentation that aligns spatial similarities across domains through a structured output space.
Learning to See through Turbulent Water Z. Li, Z. Murez, D. Kriegman, R. Ramamoorthi and M.K. Chandraker WACV 2018 [PDF]
Learning appearance and geometric priors for single-image undistortion of an image observed through a dynamic refractive medium such as water waves.
Learning Efficient Object Detection Models with Knowledge Distillation G. Chen, W. Choi, X. Yu, T. Han and M.K. Chandraker NeurIPS 2017 [PDF]
Fast and accurate object detection network through knowledge distillation that transfers insights to a compact student model from a higher-capacity teacher model.
Robust Energy Minimization for BRDF-Invariant Shape from Light Fields Z. Li, Z. Xu, R. Ramamoorthi and M.K. Chandraker CVPR 2017 [PDF]
A variational energy minimization framework for robust recovery of shape in multiview stereo with unknown BRDF, with applications to light field cameras.
Deep Supervision with Shape Concepts for Occlusion-Aware 3D Object Parsing C. Li, Z. Zia, Q.-H. Tran, X. Yu, G. Hager and M.K. Chandraker CVPR 2017 [PDF]
Deep supervision to sequentially infer intermediate concepts associated with the final task allows better generalization, demonstrated with an application to 3D semantic parsing from 2D images.
DESIRE: Distant Future Prediction in Dynamic Scenes with Multiple Interacting Agents N. Lee, W. Choi, P. Vernaza, C. Choy, P. Torr and M.K. Chandraker CVPR 2017 [PDF]
Predicting future trajectories in complex 3D scenes by accounting for the multimodaility of future behaviors, scene semantics and interactions among objects.
Universal Correspondence Network C. Choy, J. Gwak, S. Savarese and M.K. Chandraker NeurIPS 2016 (Oral) [PDF]
Deep metric learning to learn a feature space for geometric and semantic correspondence, with novel architectures such as a convolutional spatial transformer to handle local variations.
WarpNet: Weakly Supervised Matching for Single-View Reconstruction A. Kanazawa, D. Jacobs and M.K. Chandraker CVPR 2016 [PDF]
Single-view reconstruction of non-rigid objects like birds without using part annotations, through a deformation-aware synthetic data generation and spatial priors in a deep network.
SVBRDF-Invariant Shape and Reflectance Recovery from Light Fields T.-C. Wang, M.K. Chandraker, A. Efros and R. Ramamoorthi CVPR 2016 (Oral) [PDF]
Shape and spatially-varying material recovery from a single light field image of an object, using theoretical invariants from differential stereo with general reflectance.
The Information Available to a Moving Observer on Shape with Unknown, Isotropic BRDFs M.K. Chandraker IEEE PAMI 2015 [Spl. Issue, Best of CVPR 2014] [PDF]
Theoretical inavriants that eliminate BRDF from a system of differential stereo equations to yield PDE constraints that delineate the extent of shape recovery.
Joint SFM and Detection Cues in 3D Object Localization for Autonomous Driving S. Song and M.K. Chandraker CVPR 2015 (Oral) [PDF]
Single-camera 3D localization of objects in traffic scenes by combining cues from SFM point tracks and object detection bounding boxes.
What Camera Motion Reveals About Shape with Unknown BRDF M.K. Chandraker CVPR 2014 (Oral) [Best Paper Award] [PDF][Tech Report]
Specification of the extent of shape recovery through differential stereo invariants obtained using images of an object with unknown material observed under a small camera motion.
What Motion Reveals About Shape with Unknown BRDF and Lighting M.K. Chandraker, D. Reddy, Y. Wang and R. Ramamoorthi CVPR 2013 (Oral) [PDF]
Theoretical analysis of shape recovery using differential flow invariants obtained under small motions of an object relative to its environment.
Dense Object Reconstruction with Semantic Priors Y. Bao, M.K. Chandraker, Y. Lin and S. Savarese CVPR 2013 (Oral) [PDF]
Semantic 3D reconstruction using shape priors consisting of a mean shape for the commonality of shapes across a category and weighted anchor points to encode similarities between instances in the form of appearance and spatial consistency.
On Differential Photometric Reconstruction for Unknown, Isotropic BRDFs M.K. Chandraker, J. Bai and R. Ramamoorthi IEEE PAMI 2013 [Spl. Issue, Best of CVPR 2011] [PDF]
A photometric flow relation that specifies theoretical extent of shape recovery possible with differential motion of a light source.
What An Image Reveals About Material Reflectance M.K. Chandraker and R. Ramamoorthi ICCV 2011 (Oral) [PDF]
A semiparametric regression for single-image material estimation that achieves better generalization and interpretability, enabling applications such as relighting and material editing.
A Theory of Photometric Reconstruction for Unknown Isotropic Reflectances M.K. Chandraker, J. Bai and R. Ramamoorthi CVPR 2011 (Oral) [PDF]
Differential invariants under light source motion that determine the extent of shape recovery and prior information needed for it, using images of an object with unknown material.
Globally Optimal Algorithms for Stratified Autocalibration M.K. Chandraker, S. Agarwal, D.J. Kriegman and S. Belongie IJCV 2009 [PDF]
Tight convex relations in a branch and bound framework for globally optimal estimation of the plane at infinity with chirality constraints and dual image of the absolute conic with semidefinite constraints, allowing metric upgrade of a projective reconsturction.
Globally Optimal Bilinear Programming for Computer Vision Applications M.K. Chandraker and D.J. Kriegman CVPR 2008 (Oral) [PDF][Code]
Globally optimal solutions to bilinear problems through convex relations in a branch and bound framework, demonstrated for face 3D morphable model fitting and non-rigid SFM.
Globally Optimal Affine and Metric Upgrades in Stratified Autocalibration M.K. Chandraker, S. Agarwal, D.J. Kriegman and S. Belongie ICCV 2007 (Oral) [Marr Prize Honorable Mention] [PDF][Project Site]
Globally optimal metric upgrade of a projective reconstruction, through efficient convex relaxations for estimating the plane at infinity and camera intrinsic parameters.
ShadowCuts: Photometric Stereo with Shadows M.K. Chandraker, S. Agarwal and D.J. Kriegman CVPR 2007 [PDF][Data+Code]
An algorithm for performing Lambertian photometric stereo in the presence of shadows. It reduces the low frequency bias inherent to the normal integration process and ensures that the recovered surface is consistent with the shadowing configuration.
Practical Global Optimization for Multiview Geometry S. Agarwal, M.K. Chandraker, F. Kahl, D.J. Kriegman and S. Belongie ECCV 2006 (Oral) [PDF][Code]
A practical method for finding the provably globally optimal solution to numerous problems in projective geometry including multiview triangulation, camera resectioning and homography estimation.
Reflections on the Generalized Bas-Relief Ambiguity M.K. Chandraker, F. Kahl and D.J. Kriegman CVPR 2005 (Oral) [PDF]
For general nonconvex surfaces, interreflections completely resolve the GBR ambiguity. The full Euclidean geometry can be recovered from uncalibrated photometric stereo for which the light source directions and strengths are unknown.
Short bio
Manmohan Chandraker is a full professor at the CSE department of the University of California, San Diego. He received a PhD from UCSD and was a postdoctoral scholar at UC Berkeley. His research interests are in computer vision, machine learning and graphics-based vision, with applications to autonomous driving, robotics and augmented reality. His works have been recognized with the Best Paper honorable mention at ECCV 2022, Google Research Awards in 2021, 2019 and 2018, the NSF CAREER Award in 2018, the Best Paper Award at CVPR 2014, an IEEE PAMI special issue on Best Papers from CVPR 2011, the 2009 CSE Dissertation Award for Best Thesis from UCSD and the Marr Prize honorable mention at ICCV 2007. He serves in senior program committees at CVPR, ICCV, ECCV, NeurIPS and AAAI.