Manmohan Chandraker

79

Papers

1,189

Total Citations

Papers (79)

Learning Efficient Object Detection Models with Knowledge Distillation

Learning Monocular Visual Odometry via Self-Supervised Long-Term Modeling

What You See is What You GAN: Rendering Every Pixel for High-Fidelity Geometry in 3D GANs

DWIM: Towards Tool-aware Visual Reasoning via Discrepancy-aware Workflow Generation & Instruct-Masking Tuning

Instantaneous Perception of Moving Objects in 3D

AutoScape: Geometry-Consistent Long-Horizon Scene Generation

Self-Training Large Language Models for Improved Visual Program Synthesis With Visual Reinforcement

Generating Enhanced Negatives for Training Language-Based Object Detectors

Tell, Don't Show: Language Guidance Eases Transfer Across Domains in Images and Videos

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

WarpNet: Weakly Supervised Matching for Single-View Reconstruction

A Continuous Occlusion Model for Road Scene Understanding

SVBRDF-Invariant Shape and Reflectance Estimation From Light-Field Cameras

DESIRE: Distant Future Prediction in Dynamic Scenes With Interacting Agents

Person Re-Identification in the Wild

Deep Supervision With Shape Concepts for Occlusion-Aware 3D Object Parsing

Robust Energy Minimization for BRDF-Invariant Shape From Light Fields

Deep Network Flow for Multi-Object Tracking

Learning Random-Walk Label Propagation for Weakly-Supervised Semantic Segmentation

Learning to Adapt Structured Output Space for Semantic Segmentation

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

Learning Structure-And-Motion-Aware Rolling Shutter Correction

Feature Transfer Learning for Face Recognition With Under-Represented Data

A Parametric Top-View Representation of Complex Road Scenes

Through the Looking Glass: Neural 3D Reconstruction of Transparent Shapes

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

Understanding Road Layout From Videos as a Whole

Peek-a-Boo: Occlusion Reasoning in Indoor Scenes With Plane Representations

Towards Universal Representation Learning for Deep Face Recognition

Private-kNN: Practical Differential Privacy for Computer Vision

OpenRooms: An Open Framework for Photorealistic Indoor Scene Datasets

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

Cross-Domain Similarity Learning for Face Recognition in Unseen Domains

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

Instance Level Affinity-Based Transfer for Unsupervised Domain Adaptation

PhotoScene: Photorealistic Material and Lighting Transfer for Indoor Scenes

Controllable Dynamic Multi-Task Architectures

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

Learning To Learn Across Diverse Data Biases in Deep Face Recognition

On Generalizing Beyond Domains in Cross-Domain Continual Learning

Weakly but Deeply Supervised Occlusion-Reasoned Parametric Road Layouts

Q: How To Specialize Large Vision-Language Models to Data-Scarce VQA Tasks? A: Self-Train on Unlabeled Images!

NeurOCS: Neural NOCS Supervision for Monocular 3D Object Localization

GeoNet: Benchmarking Unsupervised Adaptation Across Geographies

Reconstruction-Based Disentanglement for Pose-Invariant Face Recognition

Unsupervised Domain Adaptation for Face Recognition in Unlabeled Videos

Towards Large-Pose Face Frontalization in the Wild

Domain Adaptation for Structured Output via Discriminative Patch Representations

Universal Semi-Supervised Semantic Segmentation

Modulated Periodic Activations for Generalizable Local Functional Representations

Learning Cross-Modal Contrastive Features for Video Domain Adaptation

A Theory of Topological Derivatives for Inverse Rendering of Geometry

Efficient Controllable Multi-Task Architectures

Domain Generalization Guided by Gradient Signal to Noise Ratio of Parameters

Factorized Inverse Path Tracing for Efficient and Accurate Material-Lighting Estimation

Domain Adaptive Semantic Segmentation Using Weak Labels

Locally Orderless Images for Optimization in Differentiable Rendering

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

Object Detection with a Unified Label Space from Multiple Datasets

Single-Shot Neural Relighting and SVBRDF Estimation

Improving Face Recognition by Clustering Unlabeled Faces in the Wild

SMART: Simultaneous Multi-Agent Recurrent Trajectory Prediction

A Level Set Theory for Neural Implicit Evolution under Explicit Flows

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

Learning Phase Mask for Privacy-Preserving Passive Depth Estimation

TRoVE: Transforming Road Scene Datasets into Photorealistic Virtual Environments

Exploiting Unlabeled Data with Vision and Language Models for Object Detection

Learning Semantic Segmentation from Multiple Datasets with Label Shifts

MemSAC: Memory Augmented Sample Consistency for Large Scale Domain Adaptation

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

Universal Correspondence Network

NeurIPS 2016arXiv

Single View Metrology in the Wild

LANGTRAJ: Diffusion Model and Dataset for Language-Conditioned Trajectory Simulation

TextureDreamer: Image-Guided Texture Synthesis Through Geometry-Aware Diffusion

Taming Self-Training for Open-Vocabulary Object Detection

AIDE: An Automatic Data Engine for Object Detection in Autonomous Driving

LidaRF: Delving into Lidar for Neural Radiance Field on Street Scenes

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

Exploring Question Decomposition for Zero-Shot VQA