115 citations · 662 across the 44 of their papers we have counts for
7 papers · 1 filter
Touchdown: Natural Language Navigation and Spatial Reasoning in Visual Street Environments
Howard Chen, Alane Suhr, Dipendra Misra +2
We study the problem of jointly reasoning about language and vision through a navigation and spatial reasoning task. We introduce the Touchdown task and dataset, where an agent mus…
CGIntrinsics: Better Intrinsic Image Decomposition through Physically-Based Rendering
Zhengqi Li, Noah Snavely
Intrinsic image decomposition is a challenging, long-standing computer vision problem for which ground truth data is very difficult to acquire. We explore the use of synthetic data…
Layer-structured 3D Scene Inference via View Synthesis
Shubham Tulsiani, Richard Tucker, Noah Snavely
We present an approach to infer a layer-structured 3D representation of a scene from a single input image. This allows us to infer not only the depth of the visible pixels, but als…
Discovery of Latent 3D Keypoints via End-to-end Geometric Reasoning
Supasorn Suwajanakorn, Noah Snavely, Jonathan Tompson +1
This paper presents KeypointNet, an end-to-end geometric reasoning framework to learn an optimal set of category-specific 3D keypoints, along with their detectors. Given a single i…
Stereo Magnification: Learning View Synthesis using Multiplane Images
Tinghui Zhou, Richard Tucker, John Flynn +2
The view synthesis problem--generating novel views of a scene from known imagery--has garnered recent attention due in part to compelling applications in virtual and augmented real…
Learning Intrinsic Image Decomposition from Watching the World
Zhengqi Li, Noah Snavely
Single-view intrinsic image decomposition is a highly ill-posed problem, and so a promising approach is to learn from large amounts of data. However, it is difficult to collect gro…