Search Results for author: Manmohan Chandraker

Found 79 papers, 16 papers with code

Single-Shot Neural Relighting and SVBRDF Estimation

no code implementations ECCV 2020 Shen Sang, Manmohan Chandraker

We present a novel physically-motivated deep 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.

SVBRDF Estimation

IRISformer: Dense Vision Transformers for Single-Image Inverse Rendering in Indoor Scenes

no code implementations CVPR 2022 Rui Zhu, Zhengqin Li, Janarbek Matai, Fatih Porikli, Manmohan Chandraker

Indoor scenes exhibit significant appearance variations due to myriad interactions between arbitrarily diverse object shapes, spatially-changing materials, and complex lighting.

Physically-Based Editing of Indoor Scene Lighting from a Single Image

no code implementations19 May 2022 Zhengqin Li, Jia Shi, Sai Bi, Rui Zhu, Kalyan Sunkavalli, Miloš Hašan, Zexiang Xu, Ravi Ramamoorthi, Manmohan Chandraker

We tackle this problem using two novel components: 1) a holistic scene reconstruction method that estimates scene reflectance and parametric 3D lighting, and 2) a neural rendering framework that re-renders the scene from our predictions.

Neural Rendering

A Level Set Theory for Neural Implicit Evolution under Explicit Flows

no code implementations14 Apr 2022 Ishit Mehta, Manmohan Chandraker, Ravi Ramamoorthi

Our method uses the flow field to deform parametric implicit surfaces by extending the classical theory of level sets.

Controllable Dynamic Multi-Task Architectures

no code implementations CVPR 2022 Dripta S. Raychaudhuri, Yumin Suh, Samuel Schulter, Xiang Yu, Masoud Faraki, Amit K. Roy-Chowdhury, Manmohan Chandraker

In contrast to the existing dynamic multi-task approaches that adjust only the weights within a fixed architecture, our approach affords the flexibility to dynamically control the total computational cost and match the user-preferred task importance better.

Multi-Task Learning

Single-Stream Multi-Level Alignment for Vision-Language Pretraining

no code implementations27 Mar 2022 Zaid Khan, Vijay Kumar BG, Xiang Yu, Samuel Schulter, Manmohan Chandraker, Yun Fu

In contrast, we propose a single stream model that aligns the modalities at multiple levels: i) instance level, ii) fine-grained patch level, iii) conceptual semantic level.

Referring Expression Representation Learning +2

On Generalizing Beyond Domains in Cross-Domain Continual Learning

no code implementations CVPR 2022 Christian Simon, Masoud Faraki, Yi-Hsuan Tsai, Xiang Yu, Samuel Schulter, Yumin Suh, Mehrtash Harandi, Manmohan Chandraker

Humans have the ability to accumulate knowledge of new tasks in varying conditions, but deep neural networks often suffer from catastrophic forgetting of previously learned knowledge after learning a new task.

Continual Learning Knowledge Distillation

Learning Semantic Segmentation from Multiple Datasets with Label Shifts

no code implementations28 Feb 2022 Dongwan Kim, Yi-Hsuan Tsai, Yumin Suh, Masoud Faraki, Sparsh Garg, Manmohan Chandraker, Bohyung Han

First, a gradient conflict in training due to mismatched label spaces is identified and a class-independent binary cross-entropy loss is proposed to alleviate such label conflicts.

Semantic Segmentation

YMIR: A Rapid Data-centric Development Platform for Vision Applications

1 code implementation19 Nov 2021 Phoenix X. Huang, Wenze Hu, William Brendel, Manmohan Chandraker, Li-Jia Li, Xiaoyu Wang

This paper introduces an open source platform to support the rapid development of computer vision applications at scale.

Active Learning

OpenRooms: An Open Framework for Photorealistic Indoor Scene Datasets

no code implementations CVPR 2021 Zhengqin Li, Ting-Wei Yu, Shen Sang, Sarah Wang, Meng Song, YuHan Liu, Yu-Ying Yeh, Rui Zhu, Nitesh Gundavarapu, Jia Shi, Sai Bi, Hong-Xing Yu, Zexiang Xu, Kalyan Sunkavalli, Milos Hasan, Ravi Ramamoorthi, Manmohan Chandraker

Finally, we demonstrate that our framework may also be integrated with physics engines, to create virtual robotics environments with unique ground truth such as friction coefficients and correspondence to real scenes.

Scene Understanding

Divide-and-Conquer for Lane-Aware Diverse Trajectory Prediction

no code implementations CVPR 2021 Sriram Narayanan, Ramin Moslemi, Francesco Pittaluga, Buyu Liu, Manmohan Chandraker

Our second contribution is a novel trajectory prediction framework called ALAN that uses existing lane centerlines as anchors to provide trajectories constrained to the input lanes.

Autonomous Vehicles Trajectory Prediction

Fusing the Old with the New: Learning Relative Camera Pose with Geometry-Guided Uncertainty

no code implementations CVPR 2021 Bingbing Zhuang, Manmohan Chandraker

While we focus on relative pose, we envision that our pipeline is broadly applicable for fusing classical geometry and deep learning.

Pose Estimation

Weakly But Deeply Supervised Occlusion-Reasoned Parametric Road Layouts

no code implementations CVPR 2022 Buyu Liu, Bingbing Zhuang, Manmohan Chandraker

We propose an end-to-end network that takes a single perspective RGB image of a complex road scene as input, to produce occlusion-reasoned layouts in perspective space as well as a parametric bird's-eye-view (BEV) space.

Modulated Periodic Activations for Generalizable Local Functional Representations

2 code implementations ICCV 2021 Ishit Mehta, Michaël Gharbi, Connelly Barnes, Eli Shechtman, Ravi Ramamoorthi, Manmohan Chandraker

Our approach produces generalizable functional representations of images, videos and shapes, and achieves higher reconstruction quality than prior works that are optimized for a single signal.

Instance Level Affinity-Based Transfer for Unsupervised Domain Adaptation

1 code implementation CVPR 2021 Astuti Sharma, Tarun Kalluri, Manmohan Chandraker

Domain adaptation deals with training models using large scale labeled data from a specific source domain and then adapting the knowledge to certain target domains that have few or no labels.

Unsupervised Domain Adaptation

Cross-Domain Similarity Learning for Face Recognition in Unseen Domains

no code implementations CVPR 2021 Masoud Faraki, Xiang Yu, Yi-Hsuan Tsai, Yumin Suh, Manmohan Chandraker

Intuitively, it discriminatively correlates explicit metrics derived from one domain, with triplet samples from another domain in a unified loss function to be minimized within a network, which leads to better alignment of the training domains.

Face Recognition Metric Learning

FLAVR: Flow-Agnostic Video Representations for Fast Frame Interpolation

1 code implementation15 Dec 2020 Tarun Kalluri, Deepak Pathak, Manmohan Chandraker, Du Tran

A majority of methods for video frame interpolation compute bidirectional optical flow between adjacent frames of a video, followed by a suitable warping algorithm to generate the output frames.

Action Recognition Optical Flow Estimation +1

Object Detection with a Unified Label Space from Multiple Datasets

no code implementations ECCV 2020 Xiangyun Zhao, Samuel Schulter, Gaurav Sharma, Yi-Hsuan Tsai, Manmohan Chandraker, Ying Wu

To address this challenge, we design a framework which works with such partial annotations, and we exploit a pseudo labeling approach that we adapt for our specific case.

object-detection Object Detection

Deep Keypoint-Based Camera Pose Estimation with Geometric Constraints

1 code implementation29 Jul 2020 You-Yi Jau, Rui Zhu, Hao Su, Manmohan Chandraker

Estimating relative camera poses from consecutive frames is a fundamental problem in visual odometry (VO) and simultaneous localization and mapping (SLAM), where classic methods consisting of hand-crafted features and sampling-based outlier rejection have been a dominant choice for over a decade.

Pose Estimation Simultaneous Localization and Mapping +1

SMART: Simultaneous Multi-Agent Recurrent Trajectory Prediction

no code implementations ECCV 2020 Sriram N. N, Buyu Liu, Francesco Pittaluga, Manmohan Chandraker

Our second contribution is a novel method that generates diverse predictions while accounting for scene semantics and multi-agent interactions, with constant-time inference independent of the number of agents.

Motion Forecasting Trajectory Forecasting

OpenRooms: An End-to-End Open Framework for Photorealistic Indoor Scene Datasets

no code implementations25 Jul 2020 Zhengqin Li, Ting-Wei Yu, Shen Sang, Sarah Wang, Meng Song, YuHan Liu, Yu-Ying Yeh, Rui Zhu, Nitesh Gundavarapu, Jia Shi, Sai Bi, Zexiang Xu, Hong-Xing Yu, Kalyan Sunkavalli, Miloš Hašan, Ravi Ramamoorthi, Manmohan Chandraker

Finally, we demonstrate that our framework may also be integrated with physics engines, to create virtual robotics environments with unique ground truth such as friction coefficients and correspondence to real scenes.

Multi-Task Learning Scene Understanding

Neural Mesh Flow: 3D Manifold Mesh Generation via Diffeomorphic Flows

1 code implementation NeurIPS 2020 Kunal Gupta, Manmohan Chandraker

Applications like rendering, simulations and 3D printing require meshes to be manifold so that they can interact with the world like the real objects they represent.

Improving Face Recognition by Clustering Unlabeled Faces in the Wild

no code implementations ECCV 2020 Aruni RoyChowdhury, Xiang Yu, Kihyuk Sohn, Erik Learned-Miller, Manmohan Chandraker

While deep face recognition has benefited significantly from large-scale labeled data, current research is focused on leveraging unlabeled data to further boost performance, reducing the cost of human annotation.

Face Clustering Face Recognition +2

Pseudo RGB-D for Self-Improving Monocular SLAM and Depth Prediction

no code implementations ECCV 2020 Lokender Tiwari, Pan Ji, Quoc-Huy Tran, Bingbing Zhuang, Saket Anand, Manmohan Chandraker

Classical monocular Simultaneous Localization And Mapping (SLAM) and the recently emerging convolutional neural networks (CNNs) for monocular depth prediction represent two largely disjoint approaches towards building a 3D map of the surrounding environment.

Depth Estimation Simultaneous Localization and Mapping

DAVID: Dual-Attentional Video Deblurring

no code implementations7 Dec 2019 Junru Wu, Xiang Yu, Ding Liu, Manmohan Chandraker, Zhangyang Wang

To train and evaluate on more diverse blur severity levels, we propose a Challenging DVD dataset generated from the raw DVD video set by pooling frames with different temporal windows.


Adversarial Learning of Privacy-Preserving and Task-Oriented Representations

no code implementations22 Nov 2019 Taihong Xiao, Yi-Hsuan Tsai, Kihyuk Sohn, Manmohan Chandraker, Ming-Hsuan Yang

For instance, there could be a potential privacy risk of machine learning systems via the model inversion attack, whose goal is to reconstruct the input data from the latent representation of deep networks.

Perceptual Distance Privacy Preserving

Pose-variant 3D Facial Attribute Generation

no code implementations24 Jul 2019 Feng-Ju Chang, Xiang Yu, Ram Nevatia, Manmohan Chandraker

We address the challenging problem of generating facial attributes using a single image in an unconstrained pose.

3D Reconstruction

Adaptation Across Extreme Variations using Unlabeled Domain Bridges

no code implementations5 Jun 2019 Shuyang Dai, Kihyuk Sohn, Yi-Hsuan Tsai, Lawrence Carin, Manmohan Chandraker

We tackle an unsupervised domain adaptation problem for which the domain discrepancy between labeled source and unlabeled target domains is large, due to many factors of inter and intra-domain variation.

Object Recognition Semantic Segmentation +1

Inverse Rendering for Complex Indoor Scenes: Shape, Spatially-Varying Lighting and SVBRDF from a Single Image

1 code implementation CVPR 2020 Zhengqin Li, Mohammad Shafiei, Ravi Ramamoorthi, Kalyan Sunkavalli, Manmohan Chandraker

Our inverse rendering network incorporates physical insights -- including a spatially-varying spherical Gaussian lighting representation, a differentiable rendering layer to model scene appearance, a cascade structure to iteratively refine the predictions and a bilateral solver for refinement -- allowing us to jointly reason about shape, lighting, and reflectance.

Unsupervised Domain Adaptation for Distance Metric Learning

no code implementations ICLR 2019 Kihyuk Sohn, Wenling Shang, Xiang Yu, Manmohan Chandraker

Unsupervised domain adaptation is a promising avenue to enhance the performance of deep neural networks on a target domain, using labels only from a source domain.

Face Recognition Metric Learning +1

Domain Adaptation for Structured Output via Disentangled Patch Representations

no code implementations ICLR 2019 Yi-Hsuan Tsai, Kihyuk Sohn, Samuel Schulter, Manmohan Chandraker

To this end, we propose to learn discriminative feature representations of patches based on label histograms in the source domain, through the construction of a disentangled space.

Domain Adaptation Semantic Segmentation

Active Adversarial Domain Adaptation

no code implementations16 Apr 2019 Jong-Chyi Su, Yi-Hsuan Tsai, Kihyuk Sohn, Buyu Liu, Subhransu Maji, Manmohan Chandraker

Our approach, active adversarial domain adaptation (AADA), explores a duality between two related problems: adversarial domain alignment and importance sampling for adapting models across domains.

Active Learning Domain Adaptation +3

Domain Adaptation for Structured Output via Discriminative Patch Representations

8 code implementations ICCV 2019 Yi-Hsuan Tsai, Kihyuk Sohn, Samuel Schulter, Manmohan Chandraker

Predicting structured outputs such as semantic segmentation relies on expensive per-pixel annotations to learn supervised models like convolutional neural networks.

Domain Adaptation Semantic Segmentation +1

IDD: A Dataset for Exploring Problems of Autonomous Navigation in Unconstrained Environments

2 code implementations26 Nov 2018 Girish Varma, Anbumani Subramanian, Anoop Namboodiri, Manmohan Chandraker, C. V. Jawahar

It also reflects label distributions of road scenes significantly different from existing datasets, with most classes displaying greater within-class diversity.

Autonomous Navigation Domain Adaptation +3

Universal Semi-Supervised Semantic Segmentation

1 code implementation ICCV 2019 Tarun Kalluri, Girish Varma, Manmohan Chandraker, C. V. Jawahar

In recent years, the need for semantic segmentation has arisen across several different applications and environments.

Ranked #21 on Semantic Segmentation on DensePASS (using extra training data)

Semi-Supervised Semantic Segmentation Unsupervised Domain Adaptation

Learning To Simulate

no code implementations ICLR 2019 Nataniel Ruiz, Samuel Schulter, Manmohan Chandraker

Simulation is a useful tool in situations where training data for machine learning models is costly to annotate or even hard to acquire.

Materials for Masses: SVBRDF Acquisition with a Single Mobile Phone Image

no code implementations ECCV 2018 Zhengqin Li, Kalyan Sunkavalli, Manmohan Chandraker

We propose a material acquisition approach to recover the spatially-varying BRDF and normal map of a near-planar surface from a single image captured by a handheld mobile phone camera.

Memory Warps for Learning Long-Term Online Video Representations

no code implementations28 Mar 2018 Tuan-Hung Vu, Wongun Choi, Samuel Schulter, Manmohan Chandraker

This paper proposes a novel memory-based online video representation that is efficient, accurate and predictive.

object-detection Object Detection

Learning to Look around Objects for Top-View Representations of Outdoor Scenes

no code implementations ECCV 2018 Samuel Schulter, Menghua Zhai, Nathan Jacobs, Manmohan Chandraker

Given a single RGB image of a complex outdoor road scene in the perspective view, we address the novel problem of estimating an occlusion-reasoned semantic scene layout in the top-view.

Semantic Segmentation

Feature Transfer Learning for Deep Face Recognition with Under-Represented Data

no code implementations23 Mar 2018 Xi Yin, Xiang Yu, Kihyuk Sohn, Xiaoming Liu, Manmohan Chandraker

In this paper, we propose a center-based feature transfer framework to augment the feature space of under-represented subjects from the regular subjects that have sufficiently diverse samples.

Disentanglement Face Recognition +1

Hierarchical Metric Learning and Matching for 2D and 3D Geometric Correspondences

no code implementations ECCV 2018 Mohammed E. Fathy, Quoc-Huy Tran, M. Zeeshan Zia, Paul Vernaza, Manmohan Chandraker

Further, we propose to use activation maps at different layers of a CNN, as an effective and principled replacement for the multi-resolution image pyramids often used for matching tasks.

Geometric Matching Metric Learning +1

Gotta Adapt 'Em All: Joint Pixel and Feature-Level Domain Adaptation for Recognition in the Wild

1 code implementation CVPR 2019 Luan Tran, Kihyuk Sohn, Xiang Yu, Xiaoming Liu, Manmohan Chandraker

Recent developments in deep domain adaptation have allowed knowledge transfer from a labeled source domain to an unlabeled target domain at the level of intermediate features or input pixels.

Domain Adaptation Image Generation +1

Learning random-walk label propagation for weakly-supervised semantic segmentation

no code implementations CVPR 2017 Paul Vernaza, Manmohan Chandraker

Large-scale training for semantic segmentation is challenging due to the expense of obtaining training data for this task relative to other vision tasks.

Weakly-Supervised Semantic Segmentation

Deep Supervision with Intermediate Concepts

no code implementations8 Jan 2018 Chi Li, M. Zeeshan Zia, Quoc-Huy Tran, Xiang Yu, Gregory D. Hager, Manmohan Chandraker

In this work, we explore an approach for injecting prior domain structure into neural network training by supervising hidden layers of a CNN with intermediate concepts that normally are not observed in practice.

Image Classification

Learning Efficient Object Detection Models with Knowledge Distillation

no code implementations NeurIPS 2017 Guobin Chen, Wongun Choi, Xiang Yu, Tony Han, Manmohan Chandraker

In this work, we propose a new framework to learn compact and fast ob- ject detection networks with improved accuracy using knowledge distillation [20] and hint learning [34].

Knowledge Distillation Model Compression +2

Unsupervised Domain Adaptation for Face Recognition in Unlabeled Videos

no code implementations ICCV 2017 Kihyuk Sohn, Sifei Liu, Guangyu Zhong, Xiang Yu, Ming-Hsuan Yang, Manmohan Chandraker

Despite rapid advances in face recognition, there remains a clear gap between the performance of still image-based face recognition and video-based face recognition, due to the vast difference in visual quality between the domains and the difficulty of curating diverse large-scale video datasets.

Data Augmentation Face Recognition +1

Robust Energy Minimization for BRDF-Invariant Shape From Light Fields

no code implementations CVPR 2017 Zhengqin Li, Zexiang Xu, Ravi Ramamoorthi, Manmohan Chandraker

On the other hand, recent works have explored PDE invariants for shape recovery with complex BRDFs, but they have not been incorporated into robust numerical optimization frameworks.

Deep Network Flow for Multi-Object Tracking

no code implementations CVPR 2017 Samuel Schulter, Paul Vernaza, Wongun Choi, Manmohan Chandraker

In this work, we demonstrate that it is possible to learn features for network-flow-based data association via backpropagation, by expressing the optimum of a smoothed network flow problem as a differentiable function of the pairwise association costs.

Graph Matching Multi-Object Tracking

Weakly supervised 3D Reconstruction with Adversarial Constraint

2 code implementations31 May 2017 JunYoung Gwak, Christopher B. Choy, Animesh Garg, Manmohan Chandraker, Silvio Savarese

Supervised 3D reconstruction has witnessed a significant progress through the use of deep neural networks.

3D Reconstruction

Towards Large-Pose Face Frontalization in the Wild

no code implementations ICCV 2017 Xi Yin, Xiang Yu, Kihyuk Sohn, Xiaoming Liu, Manmohan Chandraker

Despite recent advances in face recognition using deep learning, severe accuracy drops are observed for large pose variations in unconstrained environments.

3D Reconstruction Face Recognition

DESIRE: Distant Future Prediction in Dynamic Scenes with Interacting Agents

3 code implementations CVPR 2017 Namhoon Lee, Wongun Choi, Paul Vernaza, Christopher B. Choy, Philip H. S. Torr, Manmohan Chandraker

DESIRE effectively predicts future locations of objects in multiple scenes by 1) accounting for the multi-modal nature of the future prediction (i. e., given the same context, future may vary), 2) foreseeing the potential future outcomes and make a strategic prediction based on that, and 3) reasoning not only from the past motion history, but also from the scene context as well as the interactions among the agents.

Future prediction Multi Future Trajectory Prediction +1

Reconstruction-Based Disentanglement for Pose-invariant Face Recognition

no code implementations ICCV 2017 Xi Peng, Xiang Yu, Kihyuk Sohn, Dimitris Metaxas, Manmohan Chandraker

Finally, we propose a new feature reconstruction metric learning to explicitly disentangle identity and pose, by demanding alignment between the feature reconstructions through various combinations of identity and pose features, which is obtained from two images of the same subject.

Disentanglement Face Recognition +2

A 4D Light-Field Dataset and CNN Architectures for Material Recognition

no code implementations24 Aug 2016 Ting-Chun Wang, Jun-Yan Zhu, Ebi Hiroaki, Manmohan Chandraker, Alexei A. Efros, Ravi Ramamoorthi

We introduce a new light-field dataset of materials, and take advantage of the recent success of deep learning to perform material recognition on the 4D light-field.

Image Classification Material Recognition +3

Universal Correspondence Network

no code implementations NeurIPS 2016 Christopher B. Choy, JunYoung Gwak, Silvio Savarese, Manmohan Chandraker

We present a deep learning framework for accurate visual correspondences and demonstrate its effectiveness for both geometric and semantic matching, spanning across rigid motions to intra-class shape or appearance variations.

Metric Learning Semantic Similarity +1

A Continuous Occlusion Model for Road Scene Understanding

no code implementations CVPR 2016 Vikas Dhiman, Quoc-Huy Tran, Jason J. Corso, Manmohan Chandraker

We present a physically interpretable, continuous 3D model for handling occlusions with applications to road scene understanding.

Motion Segmentation object-detection +2

Deep Deformation Network for Object Landmark Localization

no code implementations3 May 2016 Xiang Yu, Feng Zhou, Manmohan Chandraker

We propose a novel cascaded framework, namely deep deformation network (DDN), for localizing landmarks in non-rigid objects.

Face Alignment Pose Estimation

WarpNet: Weakly Supervised Matching for Single-view Reconstruction

no code implementations CVPR 2016 Angjoo Kanazawa, David W. Jacobs, Manmohan Chandraker

This is in contrast to prior works that require part annotations, since matching objects across class and pose variations is challenging with appearance features alone.

Person Re-identification in the Wild

no code implementations CVPR 2017 Liang Zheng, Hengheng Zhang, Shaoyan Sun, Manmohan Chandraker, Yi Yang, Qi Tian

Our baselines address three issues: the performance of various combinations of detectors and recognizers, mechanisms for pedestrian detection to help improve overall re-identification accuracy and assessing the effectiveness of different detectors for re-identification.

Pedestrian Detection Person Recognition +1

Joint SFM and Detection Cues for Monocular 3D Localization in Road Scenes

no code implementations CVPR 2015 Shiyu Song, Manmohan Chandraker

Experiments on the KITTI dataset show the efficacy of our cues, as well as the accuracy and robustness of our 3D object localization relative to ground truth and prior works.

Autonomous Driving Motion Segmentation +4

What Camera Motion Reveals About Shape With Unknown BRDF

no code implementations CVPR 2014 Manmohan Chandraker

For the perspective case, we show that three differential motions suffice to yield surface depth for unknown isotropic BRDF and unknown directional lighting, while additional constraints are obtained with restrictions on BRDF or lighting.

Robust Scale Estimation in Real-Time Monocular SFM for Autonomous Driving

no code implementations CVPR 2014 Shiyu Song, Manmohan Chandraker

Experiments on the KITTI dataset demonstrate the accuracy of our ground plane estimation, monocular SFM and object localization relative to ground truth, with detailed comparisons to prior art.

Autonomous Driving object-detection +2

Dense Object Reconstruction with Semantic Priors

no code implementations CVPR 2013 Sid Yingze Bao, Manmohan Chandraker, Yuanqing Lin, Silvio Savarese

Given multiple images of an unseen instance, we collate information from 2D object detectors to align the structure from motion point cloud with the mean shape, which is subsequently warped and refined to approach the actual shape.

object-detection Object Detection +1

What Object Motion Reveals about Shape with Unknown BRDF and Lighting

no code implementations CVPR 2013 Manmohan Chandraker, Dikpal Reddy, Yizhou Wang, Ravi Ramamoorthi

Under orthographic projection, we prove that three differential motions suffice to yield an invariant that relates shape to image derivatives, regardless of BRDF and illumination.

Surface Reconstruction

Cannot find the paper you are looking for? You can Submit a new open access paper.