Compression of 3D mesh sequences by temporal segmentation

Luo, Guoliang; Cordier, Frédéric; Seo, Hyewon

doi:10.1002/cav.1522

Cited by 17 publications

(26 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Because the bit rate reductions using different methods for extracting the key‐frames and encoding the residual errors are very similar, we select the best result for each quantization level and compare the proposed method with previous techniques, namely, SPC , MPEG‐4 FAMC , improved SPC (im‐SPC) , and temporal segmentation (TS) (Figure ). In Figure , we show the rate‐distortion curves of the test sequences obtained by different methods.…”

Section: Resultsmentioning

confidence: 99%

“…Rate‐distortion comparison of the proposed method with previous techniques, namely, Scalable Predictive Codec (SPC) , MPEG‐4 FAMC , improved SPC (im‐SPC) , and temporal segmentation (TS) . bpvf, bits per vertex per frame.…”

Section: Resultsmentioning

confidence: 99%

“…Luo et al . proposed a compression method by temporal segmentation in which similar frames of an animated sequence are grouped in different clusters. Then, PCA is applied on each cluster to obtain the coordinates of corresponding frames in a reduced dimensional space.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Predictive compression of animated 3D models by optimized weighted blending of key‐frames

Hajizadeh

Ebrahimnezhad

2015

Computer Animation & Virtual

View full text Add to dashboard Cite

Efficient compression techniques are required for animated mesh sequences with fixed connectivity and time‐varying geometry. In this paper, we propose a key‐frame‐based technique for three‐dimensional dynamic mesh compression. First, key‐frames are extracted from the animated sequence. Extracted key‐frames are then linearly combined using blending weights to predict the vertex locations of the other frames. These blending weights play a key role in the proposed algorithm because the prediction performance and the required number of key‐frames greatly depend on these weights. We present a novel method in order to compute the optimum blending weight that makes it possible to predict location of the vertices of the non‐key frames with the minimum number of key‐frames. The residual prediction errors are finally quantized and encoded using Huffman coding and another heuristic method. Experimental results on different test sequences with various sizes, topologies, and geometries demonstrate the privileged performance of the proposed method compared with the previous techniques. Copyright © 2015 John Wiley & Sons, Ltd.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Resultsmentioning

confidence: 99%

See 1 more Smart Citation

Predictive compression of animated 3D models by optimized weighted blending of key‐frames

Hajizadeh

Ebrahimnezhad

2015

Computer Animation & Virtual

View full text Add to dashboard Cite

show abstract

“…These authors also introduced the KG distortion measure (basically the Frobenius norm of the matrix differences) used by many authors as a reference for rate-distortion evaluation. Improved results were obtained by Sattler and Sarlette [2005], who applied PCA on spatial clusters, and Luo et al [2013], who applied it on temporal clusters. Some authors have also proposed applying PCA on the space of trajectories instead of shapes; the main benefit is that it involves the eigenvalues decomposition of a covariance matrix of 3 f × 3 f instead of 3v × 3v.…”

Section: Compression Based On Prior Segmentationmentioning

confidence: 93%

3D Mesh Compression

Maglo¹,

et al. 2015

View full text Add to dashboard Cite

3D meshes are commonly used to represent virtual surface and volumes. However, their raw data representations take a large amount of space. Hence, 3D mesh compression has been an active research topic since the mid 1990s. In 2005, two very good review articles describing the pioneering works were published. Yet, new technologies have emerged since then. In this article, we summarize the early works and put the focus on these novel approaches. We classify and describe the algorithms, evaluate their performance, and provide synthetic comparisons. We also outline the emerging trends for future research.

show abstract

“…Sattler et al [SSK05] propose instead to perform Clustered Principal Analysis on the trajectories over a few frames, thus taking advantage of the fact that large regions of the mesh undergo similar motion in standard animations. Luo et al [LCS13] choose to do a temporal clustering, i.e., cluster similar poses, which is beneficial for long animations (i.e., when the number of frames is greater than the number of vertices). Finally, Váša and Skala presented a series of articles [VS07, VS09, VS10, VS11], in which they combine PCA on the trajectory space, with accurate coefficients and basis prediction and a set of optimization strategies on the traversal order.…”

Section: Compressionmentioning

confidence: 99%

A Survey on Data‐driven Dictionary‐based Methods for 3D Modeling

Lescoat

Ovsjanikov

Memari

et al. 2018

Computer Graphics Forum

View full text Add to dashboard Cite

Dictionaries are very useful objects for data analysis, as they enable a compact representation of large sets of objects through the combination of atoms. Dictionary‐based techniques have also particularly benefited from the recent advances in machine learning, which has allowed for data‐driven algorithms to take advantage of the redundancy in the input dataset and discover relations between objects without human supervision or hard‐coded rules. Despite the success of dictionary‐based techniques on a wide range of tasks in geometric modeling and geometry processing, the literature is missing a principled state‐of‐the‐art of the current knowledge in this field. To fill this gap, we provide in this survey an overview of data‐driven dictionary‐based methods in geometric modeling. We structure our discussion by application domain: surface reconstruction, compression, and synthesis. Contrary to previous surveys, we place special emphasis on dictionary‐based methods suitable for 3D data synthesis, with applications in geometric modeling and design. Our ultimate goal is to enlight the fact that these techniques can be used to combine the data‐driven paradigm with design intent to synthesize new plausible objects with minimal human intervention. This is the main motivation to restrict the scope of the present survey to techniques handling point clouds and meshes, making use of dictionaries whose definition depends on the input data, and enabling shape reconstruction or synthesis through the combination of atoms.

show abstract

Compression of 3D mesh sequences by temporal segmentation

Cited by 17 publications

References 18 publications

Predictive compression of animated 3D models by optimized weighted blending of key‐frames

Predictive compression of animated 3D models by optimized weighted blending of key‐frames

3D Mesh Compression

A Survey on Data‐driven Dictionary‐based Methods for 3D Modeling

Contact Info

Product

Resources

About