Background Face image animation generates a synthetic human face video that harmoniously integrates the identity derived from the source image and facial motion obtained from the driving video.This technology could be...Background Face image animation generates a synthetic human face video that harmoniously integrates the identity derived from the source image and facial motion obtained from the driving video.This technology could be beneficial in multiple medical fields,such as diagnosis and privacy protection.Previous studies on face animation often relied on a single source image to generate an output video.With a significant pose difference between the source image and the driving frame,the quality of the generated video is likely to be suboptimal because the source image may not provide sufficient features for the warped feature map.Methods In this study,we propose a novel face-animation scheme based on multiple sources and perspective alignment to address these issues.We first introduce a multiple-source sampling and selection module to screen the optimal source image set from the provided driving video.We then propose an inter-frame interpolation and alignment module to further eliminate the misalignment between the selected source image and the driving frame.Conclusions The proposed method exhibits superior performance in terms of objective metrics and visual quality in large-angle animation scenes compared to other state-of-the-art face animation methods.It indicates the effectiveness of the proposed method in addressing the distortion issues in large-angle animation.展开更多
Background Considerable research has been conducted in the areas of audio-driven virtual character gestures and facial animation with some degree of success.However,few methods exist for generating full-body animation...Background Considerable research has been conducted in the areas of audio-driven virtual character gestures and facial animation with some degree of success.However,few methods exist for generating full-body animations,and the portability of virtual character gestures and facial animations has not received sufficient attention.Methods Therefore,we propose a deep-learning-based audio-to-animation-and-blendshape(Audio2AB)network that generates gesture animations and ARK it's 52 facial expression parameter blendshape weights based on audio,audio-corresponding text,emotion labels,and semantic relevance labels to generate parametric data for full-body animations.This parameterization method can be used to drive full-body animations of virtual characters and improve their portability.In the experiment,we first downsampled the gesture and facial data to achieve the same temporal resolution for the input,output,and facial data.The Audio2AB network then encoded the audio,audio-corresponding text,emotion labels,and semantic relevance labels,and then fused the text,emotion labels,and semantic relevance labels into the audio to obtain better audio features.Finally,we established links between the body,gestures,and facial decoders and generated the corresponding animation sequences through our proposed GAN-GF loss function.Results By using audio,audio-corresponding text,and emotional and semantic relevance labels as input,the trained Audio2AB network could generate gesture animation data containing blendshape weights.Therefore,different 3D virtual character animations could be created through parameterization.Conclusions The experimental results showed that the proposed method could generate significant gestures and facial animations.展开更多
Purpose: To clarify the effectiveness of 3-D delivery animation software for the mother’s and husband’s satisfaction with delivery. Subjects and Method: We independently developed a software application used to disp...Purpose: To clarify the effectiveness of 3-D delivery animation software for the mother’s and husband’s satisfaction with delivery. Subjects and Method: We independently developed a software application used to display the pelvic region and explain the labor process. The study involved a collaboration with hospital staff who recruited 18 primiparous and 18 multiparous mothers who were hospitalized for delivery at Facility A. The midwife explained the process of delivery using the “Delivery Animation Software”. A self-administered, anonymous questionnaire was distributed and analyzed separately for primiparous and multiparous mothers and their husbands. Results: 1) For both primiparous and multiparous couples, both mothers and their husbands gained a significantly higher level of understanding after delivery than during pregnancy. 2) The Self-Evaluation Scale for Experience of Delivery results were as follows: “I did my best for the baby even if it was painful” was selected more often for “birth coping skills”;“reliable medical staff” was selected more often for “physiological birth process”;“the birth progressed as I expected” was selected frequently by primiparous mothers;and “the birth progressed smoothly” was selected often by multiparous mothers. 3) In terms of husbands’ satisfaction with the delivery, “I was satisfied with the delivery”, “I was given an easy-to-understand explanation”, and “They explained the process to me” was selected of primiparous and multiparous fathers. 4) All primiparous and multiparous mothers positively evaluated whether the delivery animation was helpful in understanding the process of delivery. Conclusion: The delivery animation was effective in improving the understanding and satisfaction of both the mothers and their husbands.展开更多
Video conferencing systems face the dilemma between smooth streaming and decent visual quality because traditional video compression algorithms fail to produce bitstreams low enough for bandwidth-constrained networks....Video conferencing systems face the dilemma between smooth streaming and decent visual quality because traditional video compression algorithms fail to produce bitstreams low enough for bandwidth-constrained networks.An ultra-lightweight face-animation-based method that enables better video conferencing experience is proposed in this paper.The proposed method compresses high-quality upperbody videos with ultra-low bitrates and runs efficiently on mobile devices without high-end graphics processing units(GPU).Moreover,a visual quality evaluation algorithm is used to avoid image degradation caused by extreme face poses and/or expressions,and a full resolution image composition algorithm to reduce unnaturalness,which guarantees the user experience.Experiments show that the proposed method is efficient and can generate high-quality videos at ultra-low bitrates.展开更多
As one of the important means to spread Chinese traditional culture,Chinese-style animation has been on the rise in recent years.Many excellent works have emerged,among which the Chinese animated short film series Yao...As one of the important means to spread Chinese traditional culture,Chinese-style animation has been on the rise in recent years.Many excellent works have emerged,among which the Chinese animated short film series Yao-Chinese Folktales is one of the good representatives.It aroused a strong reaction from the audience as soon as it was released on the Internet,and gave the audience a shock to their mind and vision,which has brought some thoughts to the development of Chinese-style animation.Following a linear logic chain of past-present-future Chinese-style animation’s development,this paper takes Yao-Chinese Folktales as an example and analyzes the developmental difficulties and prospects of Chinese-style animation.At the end of the paper,some suggestions about the development path of Chinese-style animation’s future are given from the aspects of creation and dissemination,for the aim of promoting the Chinese-style animation’s development and spreading the Chinese traditional culture.展开更多
The rapid development of Internet literature not only made itself the source of information about animation and the gaming industry,but also boosted the creation of super writers who are now establishing themselves as...The rapid development of Internet literature not only made itself the source of information about animation and the gaming industry,but also boosted the creation of super writers who are now establishing themselves as IP(intellectual property)producers and providers.Rather than creating literary classics,these writers prefer producing commercial novels targeted at a certain group of readers.Meanwhile,the structure of their works tends to cater to the preferences of online games and animation,with the narrative and characters in the novel adjusting accordingly.These changes have enhanced the influence of Internet literature.But an excessive emphasis on IP gradually converts the novels into scripts for games with highly stereotyped content and structure.Fastpaced writing also renders their works with a lack of polish,including such serious problems as mismatched plots and repetitive narratives.Therefore,Internet literature is in urgent need of positive guidance,as its development will be stalled due to the excessive emphasis on IP.展开更多
The informatization of higher vocational education is the future development trend,and it is also encouraged and promoted by the Ministry of Education.This article focuses on the road and bridge major,combined with th...The informatization of higher vocational education is the future development trend,and it is also encouraged and promoted by the Ministry of Education.This article focuses on the road and bridge major,combined with the author’s experience in introducing virtual simulation and three-dimensional(3D)animation technology into relevant course teaching in recent years,discusses the application of virtual simulation and 3D animation technology in higher vocational education and promotes classroom revolution,to obtain better teaching effect.展开更多
基金the Fund from Sichuan Provincial Key Laboratory of Intelligent Terminals(SCITLAB-20016).
文摘Background Face image animation generates a synthetic human face video that harmoniously integrates the identity derived from the source image and facial motion obtained from the driving video.This technology could be beneficial in multiple medical fields,such as diagnosis and privacy protection.Previous studies on face animation often relied on a single source image to generate an output video.With a significant pose difference between the source image and the driving frame,the quality of the generated video is likely to be suboptimal because the source image may not provide sufficient features for the warped feature map.Methods In this study,we propose a novel face-animation scheme based on multiple sources and perspective alignment to address these issues.We first introduce a multiple-source sampling and selection module to screen the optimal source image set from the provided driving video.We then propose an inter-frame interpolation and alignment module to further eliminate the misalignment between the selected source image and the driving frame.Conclusions The proposed method exhibits superior performance in terms of objective metrics and visual quality in large-angle animation scenes compared to other state-of-the-art face animation methods.It indicates the effectiveness of the proposed method in addressing the distortion issues in large-angle animation.
基金Supported by the National Natural Science Foundation of China (62277014)the National Key Research and Development Program of China (2020YFC1523100)the Fundamental Research Funds for the Central Universities of China (PA2023GDSK0047)。
文摘Background Considerable research has been conducted in the areas of audio-driven virtual character gestures and facial animation with some degree of success.However,few methods exist for generating full-body animations,and the portability of virtual character gestures and facial animations has not received sufficient attention.Methods Therefore,we propose a deep-learning-based audio-to-animation-and-blendshape(Audio2AB)network that generates gesture animations and ARK it's 52 facial expression parameter blendshape weights based on audio,audio-corresponding text,emotion labels,and semantic relevance labels to generate parametric data for full-body animations.This parameterization method can be used to drive full-body animations of virtual characters and improve their portability.In the experiment,we first downsampled the gesture and facial data to achieve the same temporal resolution for the input,output,and facial data.The Audio2AB network then encoded the audio,audio-corresponding text,emotion labels,and semantic relevance labels,and then fused the text,emotion labels,and semantic relevance labels into the audio to obtain better audio features.Finally,we established links between the body,gestures,and facial decoders and generated the corresponding animation sequences through our proposed GAN-GF loss function.Results By using audio,audio-corresponding text,and emotional and semantic relevance labels as input,the trained Audio2AB network could generate gesture animation data containing blendshape weights.Therefore,different 3D virtual character animations could be created through parameterization.Conclusions The experimental results showed that the proposed method could generate significant gestures and facial animations.
文摘Purpose: To clarify the effectiveness of 3-D delivery animation software for the mother’s and husband’s satisfaction with delivery. Subjects and Method: We independently developed a software application used to display the pelvic region and explain the labor process. The study involved a collaboration with hospital staff who recruited 18 primiparous and 18 multiparous mothers who were hospitalized for delivery at Facility A. The midwife explained the process of delivery using the “Delivery Animation Software”. A self-administered, anonymous questionnaire was distributed and analyzed separately for primiparous and multiparous mothers and their husbands. Results: 1) For both primiparous and multiparous couples, both mothers and their husbands gained a significantly higher level of understanding after delivery than during pregnancy. 2) The Self-Evaluation Scale for Experience of Delivery results were as follows: “I did my best for the baby even if it was painful” was selected more often for “birth coping skills”;“reliable medical staff” was selected more often for “physiological birth process”;“the birth progressed as I expected” was selected frequently by primiparous mothers;and “the birth progressed smoothly” was selected often by multiparous mothers. 3) In terms of husbands’ satisfaction with the delivery, “I was satisfied with the delivery”, “I was given an easy-to-understand explanation”, and “They explained the process to me” was selected of primiparous and multiparous fathers. 4) All primiparous and multiparous mothers positively evaluated whether the delivery animation was helpful in understanding the process of delivery. Conclusion: The delivery animation was effective in improving the understanding and satisfaction of both the mothers and their husbands.
文摘Video conferencing systems face the dilemma between smooth streaming and decent visual quality because traditional video compression algorithms fail to produce bitstreams low enough for bandwidth-constrained networks.An ultra-lightweight face-animation-based method that enables better video conferencing experience is proposed in this paper.The proposed method compresses high-quality upperbody videos with ultra-low bitrates and runs efficiently on mobile devices without high-end graphics processing units(GPU).Moreover,a visual quality evaluation algorithm is used to avoid image degradation caused by extreme face poses and/or expressions,and a full resolution image composition algorithm to reduce unnaturalness,which guarantees the user experience.Experiments show that the proposed method is efficient and can generate high-quality videos at ultra-low bitrates.
文摘As one of the important means to spread Chinese traditional culture,Chinese-style animation has been on the rise in recent years.Many excellent works have emerged,among which the Chinese animated short film series Yao-Chinese Folktales is one of the good representatives.It aroused a strong reaction from the audience as soon as it was released on the Internet,and gave the audience a shock to their mind and vision,which has brought some thoughts to the development of Chinese-style animation.Following a linear logic chain of past-present-future Chinese-style animation’s development,this paper takes Yao-Chinese Folktales as an example and analyzes the developmental difficulties and prospects of Chinese-style animation.At the end of the paper,some suggestions about the development path of Chinese-style animation’s future are given from the aspects of creation and dissemination,for the aim of promoting the Chinese-style animation’s development and spreading the Chinese traditional culture.
基金This article is funded by“Research on the realization of‘Realism-directed Transformation’in fictional Internet literature”of Sichuan Internet Literature Development Center(w222379).
文摘The rapid development of Internet literature not only made itself the source of information about animation and the gaming industry,but also boosted the creation of super writers who are now establishing themselves as IP(intellectual property)producers and providers.Rather than creating literary classics,these writers prefer producing commercial novels targeted at a certain group of readers.Meanwhile,the structure of their works tends to cater to the preferences of online games and animation,with the narrative and characters in the novel adjusting accordingly.These changes have enhanced the influence of Internet literature.But an excessive emphasis on IP gradually converts the novels into scripts for games with highly stereotyped content and structure.Fastpaced writing also renders their works with a lack of polish,including such serious problems as mismatched plots and repetitive narratives.Therefore,Internet literature is in urgent need of positive guidance,as its development will be stalled due to the excessive emphasis on IP.
基金2021 Chongqing Energy Vocational College Science and Technology Department Teaching Reform Project"Discussion and Practice of Teaching Reform of"Bridge and Culvert Engineering Construction Technology"Based on Road and Bridge Simulation Software"(202106)。
文摘The informatization of higher vocational education is the future development trend,and it is also encouraged and promoted by the Ministry of Education.This article focuses on the road and bridge major,combined with the author’s experience in introducing virtual simulation and three-dimensional(3D)animation technology into relevant course teaching in recent years,discusses the application of virtual simulation and 3D animation technology in higher vocational education and promotes classroom revolution,to obtain better teaching effect.