Abstract
In this paper we address three different computer vision tasks using a single basic architecture: depth prediction, surface normal estimation, and semantic labeling. We use a multiscale convolutional network that is able to adapt easily to each task using only small modifications, regressing from the input image to the output map directly. Our method progressively refines predictions using a sequence of scales, and captures many image details without any superpixels or low-level segmentation. We achieve state-of-the-art performance on benchmarks for all three tasks.
Keywords
Computer scienceArtificial intelligenceSegmentationPattern recognition (psychology)Task (project management)Image (mathematics)Scale (ratio)Convolutional neural networkSequence (biology)ArchitectureImage segmentationSemantics (computer science)Computer vision
Affiliated Institutions
Related Publications
UNet++: Redesigning Skip Connections to Exploit Multiscale Features in Image Segmentation
The state-of-the-art models for medical image segmentation are variants of U-Net and fully convolutional networks (FCN). Despite their success, these models have two limitations...
Fully convolutional networks for semantic segmentation
Convolutional networks are powerful visual models that yield hierarchies of features. We show that convolutional networks by themselves, trained end-to-end, pixels-to-pixels, ex...
Learning Hierarchical Features for Scene Labeling
Scene labeling consists of labeling each pixel in an image with the category of the object it belongs to. We propose a method that uses a multiscale convolutional network traine...
Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation
Spatial pyramid pooling module or encode-decoder structure are used in deep neural networks for semantic segmentation task. The former networks are able to encode multi-scale co...
UNet++: A Nested U-Net Architecture for Medical Image Segmentation
In this paper, we present UNet++, a new, more powerful architecture for medical image segmentation. Our architecture is essentially a deeply-supervised encoder-decoder network w...
Publication Info
- Year
- 2015
- Type
- article
- Citations
- 2834
- Access
- Closed
External Links
Social Impact
Altmetric
PlumX Metrics
Social media, news, blog, policy document mentions
Citation Metrics
2834
OpenAlex
Cite This
David Eigen,
Rob Fergus
(2015).
Predicting Depth, Surface Normals and Semantic Labels with a Common Multi-scale Convolutional Architecture.
.
https://doi.org/10.1109/iccv.2015.304
Identifiers
- DOI
- 10.1109/iccv.2015.304