Bharath Hariharan

Color Bind: Exploring Color Perception in Text-to-Image Models WACV 2026 Dynamics: Language-Based Representation for Inferring Rigid-Body Dynamics From Videos CVPR 2026 Flat-Pack Bench: Evaluating Spatio-Temporal Understanding in Large Vision-Language Models through Furniture Assembly CVPR 2026 Live Interactive Training for Video Segmentation CVPR 2026 MovieRecapsQA: A Multimodal Open-Ended Video Question-Answering Benchmark CVPR 2026 3D Synthesis for Architectural Design WACV 2025 Accurate Differential Operators for Hybrid Neural Fields CVPR 2025 DiSciPLE: Learning Interpretable Programs for Scientific Visual Discovery CVPR 2025 FlashDepth: Real-time Streaming Video Depth Estimation at 2K Resolution ICCV 2025 Generating 3D-Consistent Videos from Unposed Internet Photos CVPR 2025 Learning 3D Perception from Others' Predictions ICLR 2025 Mixed Signals: A Diverse Point Cloud Dataset for Heterogeneous LiDAR V2X Collaboration ICCV 2025 Scale-aware Recognition in Satellite Images under Resource Constraints ICLR 2025 Transfer Your Perspective: Controllable 3D Generation from Any Viewpoint in a Driving Scene CVPR 2025 AllClear: A Comprehensive Dataset and Benchmark for Cloud Removal in Satellite Imagery NeurIPS 2024 Counter-Current Learning: A Biologically Plausible Dual Network Approach for Deep Learning NeurIPS 2024 DiffuBox: Refining 3D Object Detection with Point Diffusion NeurIPS 2024 MegaScenes: Scene-Level View Synthesis at Scale ECCV 2024 MOD-UV: Learning Mobile Object Detectors from Unlabeled Videos ECCV 2024 Pre-training LiDAR-based 3D Object Detectors through Colorization ICLR 2024 Remote Sensing Vision-Language Foundation Models without Annotations via Ground Remote Alignment ICLR 2024 Change-Aware Sampling and Contrastive Learning for Satellite Images CVPR 2023 Distilling from Similar Tasks for Transfer Learning on a Budget ICCV 2023 Doppelgangers: Learning to Disambiguate Images of Similar Structures ICCV 2023 Dynamo-Depth: Fixing Unsupervised Depth Estimation for Dynamical Scenes NeurIPS 2023 Emergent Correspondence from Image Diffusion NeurIPS 2023 Reward Finetuning for Faster and More Accurate Unsupervised Object Discovery NeurIPS 2023 Tracking Everything Everywhere All at Once ICCV 2023 Change Event Dataset for Discovery from Spatio-temporal Remote Sensing Imagery NeurIPS 2022 Hindsight is 20/20: Leveraging Past Traversals to Aid 3D Perception ICLR 2022 Ithaca365: Dataset and Driving Perception Under Repeated and Challenging Weather Conditions CVPR 2022 Learning To Detect Mobile Objects From LiDAR Scans Without Labels CVPR 2022 Polynomial Neural Fields for Subband Decomposition and Manipulation NeurIPS 2022 Unsupervised Adaptation from Repeated Traversals for Autonomous Driving NeurIPS 2022 Unsupervised Semantic Segmentation by Distilling Feature Correspondences ICLR 2022 Visual Prompt Tuning ECCV 2022 Can We Characterize Tasks Without Labels or Features? CVPR 2021 Coarsely-Labeled Data for Better Few-Shot Transfer ICCV 2021 Extreme Rotation Estimation Using Dense Correlation Volumes CVPR 2021 Few-Shot Classification With Feature Map Reconstruction Networks CVPR 2021 Field-Guide-Inspired Zero-Shot Learning ICCV 2021 Geometry Processing with Neural Fields NeurIPS 2021 PiCIE: Unsupervised Semantic Segmentation Using Invariance and Equivariance in Clustering CVPR 2021 Self-training For Few-shot Transfer Across Extreme Task Differences ICLR 2021 Stay Positive: Non-Negative Image Synthesis for Augmented Reality CVPR 2021 End-to-End Pseudo-LiDAR for Image-Based 3D Object Detection CVPR 2020 Extending and Analyzing Self-Supervised Learning Across Domains ECCV 2020 Fashionpedia: Ontology, Segmentation, and an Attribute Localization Dataset ECCV 2020 Learning Feature Descriptors using Camera Pose Supervision ECCV 2020 Learning Gradient Fields for Shape Generation ECCV 2020 Pseudo-LiDAR++: Accurate Depth for 3D Object Detection in Autonomous Driving ICLR 2020 Revisiting Pose-Normalization for Fine-Grained Few-Shot Recognition CVPR 2020 Train in Germany, Test in the USA: Making 3D Object Detectors Generalize CVPR 2020 Wasserstein Distances for Stereo Disparity Estimation NeurIPS 2020 When Does Self-supervision Improve Few-shot Learning? ECCV 2020 Few-Shot Generalization for Single-Image 3D Reconstruction via Priors ICCV 2019 Few-Shot Learning With Localization in Realistic Settings CVPR 2019 GeoStyle: Discovering Fashion Trends and Events ICCV 2019 On the Efficacy of Knowledge Distillation ICCV 2019 PointFlow: 3D Point Cloud Generation With Continuous Normalizing Flows ICCV 2019 Pseudo-LiDAR From Visual Depth Estimation: Bridging the Gap in 3D Object Detection for Autonomous Driving CVPR 2019 Learning Single-View 3D Reconstruction with Limited Pose Supervision ECCV 2018 Low-Shot Learning From Imaginary Data CVPR 2018 Low-Shot Learning With Large-Scale Diffusion CVPR 2018 Resource Aware Person Re-Identification Across Multiple Resolutions CVPR 2018 CLEVR: A Diagnostic Dataset for Compositional Language and Elementary Visual Reasoning CVPR 2017 Feature Pyramid Networks for Object Detection CVPR 2017 Inferring and Executing Programs for Visual Reasoning ICCV 2017 Learning Features by Watching Objects Move CVPR 2017 Low-Shot Visual Recognition by Shrinking and Hallucinating Features ICCV 2017 Iterative Instance Segmentation CVPR 2016 Multi-Task Learning for Straggler Avoiding Predictive Job Scheduling JMLR 2016 DeepBox: Learning Objectness With Convolutional Networks ICCV 2015 Hypercolumns for Object Segmentation and Fine-Grained Localization CVPR 2015 Detecting Objects using Deformation Dictionaries CVPR 2014 Using k-Poselets for Detecting People and Localizing Their Keypoints CVPR 2014