Resizing by symmetry-summarization

Wu, Huisi; Wang, Yu-Shuen; Feng, Kun-Chuan; Wong, Tien‐Tsin; Lee, Tong‐Yee; Heng, Pheng‐Ann

doi:10.1145/1866158.1866185

Cited by 31 publications

(31 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Cropping [Chen et al 2003;Liu et al 2003;Suh et al 2003;Santella et al 2006], seam or region carving [Avidan and Shamir 2007;Rubinstein et al 2008;Pritch et al 2009] and patch-based approaches [Simakov et al 2008;Cho et al 2008;Barnes et al 2009] all discard, duplicate and/or rearrange discrete portions of the image to minimize the distortion of salient image parts. They achieve excellent results, especially when several operators are combined [Rubinstein et al 2009;Dong et al 2009;Wu et al 2010], as confirmed by a recent comprehensive user study [Rubinstein et al 2010]. However, achieving temporal coherence for discrete approaches is challenging in our context, since the forward and backward mappings between the original and resized images are not each other's inverses.…”

Section: Related Worksupporting

confidence: 55%

Scalable and coherent video resizing with per-frame optimization

WangYu-Shuen¹,

HsiaoJen-Hung²,

SorkineOlga³

2011

ACM Trans. Graph.

Self Cite

View full text Add to dashboard Cite

original video cube deformed video cube original frames deformed frames Figure 1: We introduce a scalable content-aware video retargeting method. Here, we render pairs of original and deformed motion trajectories in red and blue. Making the relative transformation of such pathlines consistent ensures temporal coherence of the resized video. AbstractThe key to high-quality video resizing is preserving the shape and motion of visually salient objects while remaining temporallycoherent. These spatial and temporal requirements are difficult to reconcile, typically leading existing video retargeting methods to sacrifice one of them and causing distortion or waving artifacts. Recent work enforces temporal coherence of content-aware video warping by solving a global optimization problem over the entire video cube. This significantly improves the results but does not scale well with the resolution and length of the input video and quickly becomes intractable. We propose a new method that solves the scalability problem without compromising the resizing quality. Our method factors the problem into spatial and time/motion components: we first resize each frame independently to preserve the shape of salient regions, and then we optimize their motion using a reduced model for each pathline of the optical flow. This factorization decomposes the optimization of the video cube into sets of subproblems whose size is proportional to a single frame's resolution and which can be solved in parallel. We also show how to incorporate cropping into our optimization, which is useful for scenes with numerous salient objects where warping alone would degenerate to linear scaling. Our results match the quality of state-of-the-art retargeting methods while dramatically reducing the computation time and memory consumption, making content-aware video resizing scalable and practical.

show abstract

Section: Related Worksupporting

confidence: 55%

Scalable and coherent video resizing with per-frame optimization

WangYu-Shuen¹,

HsiaoJen-Hung²,

SorkineOlga³

2011

ACM Trans. Graph.

Self Cite

View full text Add to dashboard Cite

show abstract

“…Third, co-segmentation systems are often computationally demanding, especially, on a large number of images. In practice, applications such as image retargeting [27], object location and recognition [28], only need to roughly but quickly localize the common objects from the multiple images. Unlike co-segmentation, our co-saliency detection method automatically discriminates the common salient objects.…”

Section: Introductionmentioning

confidence: 99%

Cluster-Based Co-Saliency Detection

Cao

2013

IEEE Trans. on Image Process.

396

283

View full text Add to dashboard Cite

Co-saliency is used to discover the common saliency on the multiple images, which is a relatively under-explored area. In this paper, we introduce a new cluster-based algorithm for co-saliency detection. Global correspondence between the multiple images is implicitly learned during the clustering process. Three visual attention cues: contrast, spatial, and corresponding, are devised to effectively measure the cluster saliency. The final co-saliency maps are generated by fusing the single image saliency and multi-image saliency. The advantage of our method is mostly bottom-up without heavy learning, and has the property of being simple, general, efficient, and effective. Quantitative and qualitative experimental results on a variety of benchmark datasets demonstrate the advantages of the proposed method over the competing co-saliency methods, and our method on single image also outperforms most the state-of-the-art saliency detection methods. Furthermore, we apply the co-saliency method on four vision applications: co-segmentation, robust image distance, weakly supervised learning, and video foreground detection, which demonstrate the potential usages of the co-saliency map.

show abstract

“…A primary example is example-based texture synthesis [Wei et al 2009] where the imitated styles are mainly of a local nature. Recently, such techniques have been extended to preserve more global structures in images [Risser et al 2010;Wu et al 2010]. …”

Section: Introductionmentioning

confidence: 99%

“…Such minimization avoids deforming the elements beyond what their semantic or engineering constraints would allow. Existing methods on retargeting architectural scenes have operated on image data with the recent work of Wu et al [2010] being structure-oriented. Their work focuses on retargeting detected regular grid structures only.…”

Section: Introductionmentioning

confidence: 99%

“…Many modern architectural models, even the building facades alone, present amazing varieties including irregularities in diverse forms (see figures throughout the paper). Such models cannot be easily parsed by grammar-based methods [Wonka et al 2003;Aliaga et al 2007;Mueller et al 2006], nor can they be handled by the method of Wu et al [2010] since the facade cannot be expressed by a grid, an aggregation of sub-grids, nor is there a simple partition into floors of a regular structure. Our technique aims to retarget architecture scenes exhibiting general irregularities and it operates in the 3D object space.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Structure-preserving retargeting of irregular 3D architecture

LinJinjie¹,

Cohen-OrDaniel

ZhangHao

et al. 2011

ACM Trans. Graph.

View full text Add to dashboard Cite

Figure 1: Retargeting of a real-world irregular 3D architectural model (photo at bottom-left corner) while preserving its structural style. AbstractWe present an algorithm for interactive structure-preserving retargeting of irregular 3D architecture models, offering the modeler an easy-to-use tool to quickly generate a variety of 3D models that resemble an input piece in its structural style. Working on a more global and structural level of the input, our technique allows and even encourages replication of its structural elements, while taking into account their semantics and expected geometric interrelations such as alignments and adjacency. The algorithm performs automatic replication and scaling of these elements while preserving their structures. Instead of formulating and solving a complex constrained optimization, we decompose the input model into a set of sequences, each of which is a 1D structure that is relatively straightforward to retarget. As the sequences are retargeted in turn, they progressively constrain the retargeting of the remaining sequences. We demonstrate interactivity and variability of results from our retargeting algorithm using many examples modeled after real-world architectures exhibiting various forms of irregularity.

show abstract

Resizing by symmetry-summarization

Cited by 31 publications

References 36 publications

Scalable and coherent video resizing with per-frame optimization

Scalable and coherent video resizing with per-frame optimization

Cluster-Based Co-Saliency Detection

Structure-preserving retargeting of irregular 3D architecture

Contact Info

Product

Resources

About