Name
Abstract | ||
|---|---|---|
We present a method for computing ambient occlusion (AO) for a stack of images of a Lambertian scene from a fixed viewpoint. Ambient occlusion, a concept common in computer graphics, characterizes the local visibility at a point: it approximates how much light can reach that point from different directions without getting blocked by other geometry. While AO has received surprisingly little attention in vision, we show that it can be approximated using simple, per-pixel statistics over image stacks, based on a simplified image formation model. We use our derived AO measure to compute reflectance and illumination for objects without relying on additional smoothness priors, and demonstrate state-of-the art performance on the MIT Intrinsic Images benchmark. We also demonstrate our method on several synthetic and real scenes, including 3D printed objects with known ground truth geometry. |
Year | DOI | Venue |
|---|---|---|
2016 | 10.1109/TPAMI.2015.2453959 | IEEE Transactions Pattern Analysis and Machine Intelligence |
Keywords | Field | DocType |
computational geometry,computer vision,natural scenes,photometry,3D printed objects,AO measure,Lambertian scene,MIT intrinsic Image benchmark,computer graphics,fixed viewpoint,ground truth geometry,illumination,image stacks,intrinsic image decomposition,per-pixel statistics,photometric ambient occlusion,reflectance,simplified image formation model,Ambient occlusion,image stacks,intrinsic images,pixel statistics | Computer vision,Visibility,Computer science,Photometry (optics),Image formation,Ground truth,Ambient occlusion,Artificial intelligence,Smoothness,Prior probability,Computer graphics | Journal |
Volume | Issue | ISSN |
38 | 4 | 0162-8828 |
Citations | PageRank | References |
3 | 0.39 | 21 |
Authors | ||
4 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Daniel Cabrini Hauagge | 1 | 3 | 0.73 |
| Scott Wehrwein | 2 | 17 | 2.29 |
| Kavita Bala | 3 | 2046 | 138.75 |
| Noah Snavely | 4 | 4262 | 197.04 |