Yihong Lin, Xuemiao Xu, Huaidong Zhang, Cheng Xu, Weijie Li, Yi Xie, Jing Qin, Shengfeng He
{"title":"广义一次性神经人类渲染的不可见语义研究。","authors":"Yihong Lin, Xuemiao Xu, Huaidong Zhang, Cheng Xu, Weijie Li, Yi Xie, Jing Qin, Shengfeng He","doi":"10.1109/TVCG.2025.3563229","DOIUrl":null,"url":null,"abstract":"<p><p>Traditional human neural radiance fields often overlook crucial body semantics, resulting in ambiguous reconstructions, particularly in occluded regions. To address this problem, we propose the Super-Semantic Disentangled Neural Renderer (SSD-NeRF), which employs rich regional semantic priors to enhance human rendering accuracy. This approach initiates with a Visible-Invisible Semantic Propagation module, ensuring coherent semantic assignment to occluded parts based on visible body segments. Furthermore, a Region-Wise Texture Propagation module independently extends textures from visible to occluded areas within semantic regions, thereby avoiding irrelevant texture mixtures and preserving semantic consistency. Additionally, a view-aware curricular learning approach is integrated to bolster the model's robustness and output quality across different viewpoints. Extensive evaluations confirm that SSD-NeRF surpasses leading methods, particularly in generating quality and structurally semantic reconstructions of unseen or occluded views and poses.</p>","PeriodicalId":94035,"journal":{"name":"IEEE transactions on visualization and computer graphics","volume":"PP ","pages":""},"PeriodicalIF":0.0000,"publicationDate":"2025-04-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Delving into Invisible Semantics for Generalized One-shot Neural Human Rendering.\",\"authors\":\"Yihong Lin, Xuemiao Xu, Huaidong Zhang, Cheng Xu, Weijie Li, Yi Xie, Jing Qin, Shengfeng He\",\"doi\":\"10.1109/TVCG.2025.3563229\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p><p>Traditional human neural radiance fields often overlook crucial body semantics, resulting in ambiguous reconstructions, particularly in occluded regions. To address this problem, we propose the Super-Semantic Disentangled Neural Renderer (SSD-NeRF), which employs rich regional semantic priors to enhance human rendering accuracy. This approach initiates with a Visible-Invisible Semantic Propagation module, ensuring coherent semantic assignment to occluded parts based on visible body segments. Furthermore, a Region-Wise Texture Propagation module independently extends textures from visible to occluded areas within semantic regions, thereby avoiding irrelevant texture mixtures and preserving semantic consistency. Additionally, a view-aware curricular learning approach is integrated to bolster the model's robustness and output quality across different viewpoints. Extensive evaluations confirm that SSD-NeRF surpasses leading methods, particularly in generating quality and structurally semantic reconstructions of unseen or occluded views and poses.</p>\",\"PeriodicalId\":94035,\"journal\":{\"name\":\"IEEE transactions on visualization and computer graphics\",\"volume\":\"PP \",\"pages\":\"\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2025-04-22\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"IEEE transactions on visualization and computer graphics\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/TVCG.2025.3563229\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"IEEE transactions on visualization and computer graphics","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/TVCG.2025.3563229","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
Delving into Invisible Semantics for Generalized One-shot Neural Human Rendering.
Traditional human neural radiance fields often overlook crucial body semantics, resulting in ambiguous reconstructions, particularly in occluded regions. To address this problem, we propose the Super-Semantic Disentangled Neural Renderer (SSD-NeRF), which employs rich regional semantic priors to enhance human rendering accuracy. This approach initiates with a Visible-Invisible Semantic Propagation module, ensuring coherent semantic assignment to occluded parts based on visible body segments. Furthermore, a Region-Wise Texture Propagation module independently extends textures from visible to occluded areas within semantic regions, thereby avoiding irrelevant texture mixtures and preserving semantic consistency. Additionally, a view-aware curricular learning approach is integrated to bolster the model's robustness and output quality across different viewpoints. Extensive evaluations confirm that SSD-NeRF surpasses leading methods, particularly in generating quality and structurally semantic reconstructions of unseen or occluded views and poses.