We consider the problem of estimating detailed 3-d structure from a single still image of an unstructured environment. Our goal is to create 3-d models which are both quantitatively accurate as well as visually pleasing.
For each small homogeneous patch in the image, we use a Markov Random Field (MRF) to infer a set of "plane parameters" that capture both the 3-d location and 3-d orientation of the patch. The MRF, trained via supervised learning, models both image depth cues as well as the relationships between different parts of the image. Other than assuming that the environment is made up of a number of small planes, our model makes no explicit assumptions about the structure of the scene; this enables the algorithm to capture much more detailed 3-d structure than does prior art, and also give a much richer experience in the 3-d flythroughs created using image-based rendering, even for scenes with significant non-vertical structure.
Using this approach, we have created qualitatively correct 3-d models for 64.9% of 588 images downloaded from the internet. We have also extended our model to produce large scale 3d models from a few images.
MoreResults
Training DataDetailed Results on 588+134 images (Nov 2006)Multi-view results (Jun 2007)Make 3D model from your image
http://make3d.stanford.edu(In two simple steps: upload and browse-in-3d !)
Publications
Learning 3-D Scene Structure from a Single Still Image,
Ashutosh Saxena, Min Sun, Andrew Y. Ng, In ICCV workshop on 3D Representation for Recognition (3dRR-07), 2007. (best paper) [
ps,
pdf,
ppt]
3-D Reconstruction from Sparse Views using Monocular Vision,
Ashutosh Saxena, Min Sun, Andrew Y. Ng, In ICCV workshop on Virtual Representations and Modeling of Large-scale environments (VRML), 2007. [
ps,
pdf]
Also see
related publications:
Learning depth from single monocular images,
Ashutosh Saxena, Sung H. Chung, Andrew Y. Ng. In NIPS 18, 2005.
3-D Depth Reconstruction from a Single Still Image,
Ashutosh Saxena, Sung H. Chung, Andrew Y. Ng. IJCV, Aug 2007.
Links
People:
Ashutosh Saxena,
Min Sun,
Andrew Y. NgReconstruction3d group WikiMonocular Depth EstimationImproving Stereo-visionAutonomous driving using monocular visionIndoor single image 3-d reconstruction (
More)
Outdoor single image "popups"Original Single Still Image
Predicted 3-d model (mesh-view).
Snapshot of the predicted 3-d flythrough.
3-d flythrough (requires shockwave).
本站仅提供存储服务,所有内容均由用户发布,如发现有害或侵权内容,请
点击举报。