activity
20162023
most citedInverse Rendering for Complex Indoor Scenes: Shape, Spatially-Varying Lighting and SVBRDF from a Single Image

16 citations · 86 across the 40 of their papers we have counts for

collaborators
Showing 2022 · cs.CVShow all

14 papers · 2 filters

cs.CV2022

Long-HOT: A Modular Hierarchical Approach for Long-Horizon Object Transport

Sriram Narayanan, Dinesh Jayaraman, Manmohan Chandraker

We address key challenges in long-horizon embodied exploration and navigation by proposing a new object transport task and a novel modular framework for temporally extended navigat…

cs.CV2022★ 1 cited

IDD-3D: Indian Driving Dataset for 3D Unstructured Road Scenes

Shubham Dokania, A. H. Abdul Hafez, Anbumani Subramanian +2

Autonomous driving and assistance systems rely on annotated data from traffic and road scenarios to model and learn the various object relations in complex real-world scenarios. Pr…

cs.CV2022

TRoVE: Transforming Road Scene Datasets into Photorealistic Virtual Environments

Shubham Dokania, Anbumani Subramanian, Manmohan Chandraker +1

High-quality structured data with rich annotations are critical components in intelligent vehicle systems dealing with road scenes. However, data curation and annotation require in…

cs.CV2022★ 2 cited

Cluster-to-adapt: Few Shot Domain Adaptation for Semantic Segmentation across Disjoint Labels

Tarun Kalluri, Manmohan Chandraker

Domain adaptation for semantic segmentation across datasets consisting of the same categories has seen several recent successes. However, a more general scenario is when the source…

cs.CV2022★ 2 cited

Exploiting Unlabeled Data with Vision and Language Models for Object Detection

Shiyu Zhao, Zhixing Zhang, Samuel Schulter +5

Building robust and generic object detection frameworks requires scaling to larger label spaces and bigger training datasets. However, it is prohibitively costly to acquire annotat…

cs.CV2022★ 1 cited

PhotoScene: Photorealistic Material and Lighting Transfer for Indoor Scenes

Yu-Ying Yeh, Zhengqin Li, Yannick Hold-Geoffroy +5

Most indoor 3D scene reconstruction methods focus on recovering 3D geometry and scene layout. In this work, we go beyond this to propose PhotoScene, a framework that takes input im…