Shape Matching and Object Recognition Using Low Distortion Correspondences

Berg, Alexander C.; Berg, Tamara L.; Malik, Jitendra

doi:10.1109/cvpr.2005.320

Cited by 660 publications

(633 citation statements)

References 30 publications

Supporting

Mentioning

622

Contrasting

Unclassified

Order By: Relevance

“…Sophisticated object representations [4], [6], [19], [57] have been developed to cope with the variations of object shapes and appearances. However, these methods still typically In this work, we are interested in a new, higher level of image alignment: aligning two images from different 3D scenes but sharing similar scene characteristics.…”

Section: Introductionmentioning

confidence: 99%

SIFT Flow: Dense Correspondence Across Scenes and Its Applications

Liu¹,

Yuen²,

Torralba³

2016

Dense Image Correspondences for Computer Vision

458

855

View full text Add to dashboard Cite

Abstract-While image alignment has been studied in different areas of computer vision for decades, aligning images depicting different scenes remains a challenging problem. Analogous to optical flow where an image is aligned to its temporally adjacent frame, we propose SIFT flow, a method to align an image to its nearest neighbors in a large image corpus containing a variety of scenes. The SIFT flow algorithm consists of matching densely sampled, pixel-wise SIFT features between two images, while preserving spatial discontinuities. The SIFT features allow robust matching across different scene/object appearances, whereas the discontinuitypreserving spatial model allows matching of objects located at different parts of the scene. Experiments show that the proposed approach robustly aligns complex scene pairs containing significant spatial differences. Based on SIFT flow, we propose an alignmentbased large database framework for image analysis and synthesis, where image information is transferred from the nearest neighbors to a query image according to the dense scene correspondence. This framework is demonstrated through concrete applications, such as motion field prediction from a single image, motion synthesis via object transfer, satellite image registration and face recognition.

show abstract

Section: Introductionmentioning

confidence: 99%

SIFT Flow: Dense Correspondence Across Scenes and Its Applications

Liu¹,

Yuen²,

Torralba³

2016

Dense Image Correspondences for Computer Vision

458

855

View full text Add to dashboard Cite

show abstract

“…A ubiquitous phenomenon in vision perception is that a single object can exhibit infinite geometric variation in the observed data following the change of extrinsic factors such as sensor parameters and global object pose 3 . In the case of 3D data where the observation also lies in a 3D Euclidean space, different sensor parameters and/or global object poses usually lead to observations that differ by a similarity transformation (translation/rotation/scaling).…”

Section: Main Obstacle -Extrinsic Factorsmentioning

confidence: 99%

“…2 When a bijective mapping between S 1 ⊂ R 3 and S 2 ⊂ R 3 is required, the feasible solution can be defined as all diffeomorphisms that map S 1 to S 2 . 3 Photometric variation can be caused by the change of illumination. We mostly focus on the geometric aspect here but the extension to the photometric aspect can be done analogously.…”

Section: Main Obstacle -Extrinsic Factorsmentioning

confidence: 99%

“…It is a fundamental problem in computer vision, computer graphics, medical image analysis and has been widely investigated in numerous important applications such as 3D surface matching and reconstruction [5,32,12,30,7,21], statistical shape modeling and knowledge-based segmentation [16,15,22,34], feature correspondence and image registration [28,38,1,20], shape similarity and object recognition [2,3,29]. Let S ⊂ R 3 denote a shape 1 .…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Modeling Shapes with Higher-Order Graphs: Methodology and Applications

Wang

Zeng

Samaras

et al. 2013

Shape Perception in Human and Computer Vision

View full text Add to dashboard Cite

Extrinsic factors such as object pose and camera parameters are a main source of shape variability and pose an obstacle to efficiently solving shape matching and inference. Most existing methods address the influence of extrinsic factors by decomposing the transformation of the source shape (model) into two parts: one corresponding to the extrinsic factors and the other accounting for intra-class variability and noise, which are solved in a successive or alternating manner. In this chapter, we consider a methodology to circumvent the influence of extrinsic factors by exploiting shape properties that are invariant to them. Based on higher-order graph-based models, we implement such a methodology to address various important vision problems, such as non-rigid 3D surface matching and knowledge-based 3D segmentation, in a one-shot optimization scheme. Experimental results demonstrate the superior performance and potential of this type of approach.

show abstract

“…Semi-local parts are found in a weakly supervised manner, i.e., from cluttered, unsegmented training images, via a direct search for visual correspondence. 2 The intractable problem of simultaneous alignment of multiple images is reduced to pairwise matching: Candidate parts are initialized by matching several training pairs and then validated against additional images.…”

Section: Semi-local Partsmentioning

confidence: 99%

A Discriminative Framework for Texture and Object Recognition Using Local Image Features

Lazebnik

Schmid

Ponce

2006

Toward Category-Level Object Recognition

View full text Add to dashboard Cite

Abstract. This chapter presents an approach for texture and object recognition that uses scale-or affine-invariant local image features in combination with a discriminative classifier. Textures are represented using a visual dictionary found by quantizing appearance-based descriptors of local features. Object classes are represented using a dictionary of composite semi-local parts, or groups of nearby features with stable and distinctive appearance and geometric layout. A discriminative maximum entropy framework is used to learn the posterior distribution of the class label given the occurrences of parts from the dictionary in the training set. Experiments on two texture and two object databases demonstrate the effectiveness of this framework for visual classification.

show abstract

Shape Matching and Object Recognition Using Low Distortion Correspondences

Abstract: Abstract

Cited by 660 publications

References 30 publications

SIFT Flow: Dense Correspondence Across Scenes and Its Applications

SIFT Flow: Dense Correspondence Across Scenes and Its Applications

Modeling Shapes with Higher-Order Graphs: Methodology and Applications

A Discriminative Framework for Texture and Object Recognition Using Local Image Features

Contact Info

Product

Resources

About