Learn More
In the past few years, convolutional neural nets (CNN) have shown incredible promise for learning visual representations. In this paper, we use CNNs for the task of predicting surface normals from a single image. But what is the right architecture? We propose to build upon the decades of hard work in 3D scene understanding to design a new CNN architecture(More)
Our everyday objects support various tasks and can be used by people for different purposes. While object classification is a widely studied topic in computer vision, recognition of object function, i.e., what people can do with an object and how they do it, is rarely addressed. In this paper we construct a functional object description with the aim to(More)
What primitives should we use to infer the rich 3D world behind an image? We argue that these primitives should be both visually discriminative and geometrically informative and we present a technique for discovering such primitives. We demonstrate the utility of our primitives by using them to infer 3D surface normals given a single image. Our technique(More)
We present an approach which exploits the coupling between human actions and scene geometry to use human pose as a cue for single-view 3D scene understanding. Our method builds upon recent advances in still-image pose estimation to extract functional and geometric constraints on the scene. These constraints are then used to improve single-view 3D scene(More)
Given a static scene, a human can trivially enumerate the myriad of things that can happen next and characterize the relative likelihood of each. In the process, we make use of enormous amounts of commonsense knowledge about how the world works. In this paper, we investigate learning this commonsense knowledge from data. To overcome a lack of densely(More)
In this work, we present a method for single-view reasoning about 3D surfaces and their relationships. We propose the use of mid-level constraints for 3D scene understanding in the form of convex and concave edges and introduce a generic framework capable of incorporating these and other constraints. Our method takes a variety of cues and uses them to infer(More)
[1] Achieving a representative elementary volume (REV) has become a de facto criterion for demonstrating the quality of lCT measurements in porous media systems. However, the data quality implications of an REV requirement have not been previously examined. In this work, deterministic REVs for porosity, moisture saturation (S W), and air-water interfacial(More)
Detect and match SIFT features using the standard procedure due to Lowe Spatial Analysis Robust Fitting and Stability Check Compute initial local planar hypotheses in the transformation domain with J­linkage Clustering the local planar hypotheses into global hypotheses Eliminate outliers in the spatial domain with a Delaunay triangulation Robustly fit the(More)
Do we really need 3D labels in order to learn how to predict 3D? In this paper, we show that one can learn a mapping from appearance to 3D properties without ever seeing a single explicit 3D label. Rather than use explicit supervision, we use the regularity of indoor scenes to learn the mapping in a completely unsupervised manner. We demonstrate this on(More)
In this paper we investigate 3D attributes as a means to understand the shape of an object in a single image. To this end, we make a number of contributions: (i) we introduce and define a set of 3D Shape attributes, including planarity, symmetry and occupied space, (ii) we show that such properties can be successfully inferred from a single image using a(More)