IEEE Transactions on Pattern Analysis and Machine Intelligence最新文献_第10页

Rendering Humans behind Occlusions 渲染遮挡后的人类

IF 23.6 1区计算机科学

IEEE Transactions on Pattern Analysis and Machine Intelligence Pub Date : 2025-08-27 DOI: 10.1109/tpami.2025.3603154

Tiange Xiang, Adam Sun, Scott Delp, Kazuki Kozuka, Li Fei-Fei, Ehsan Adeli

引用次数: 0

OccScene: Semantic Occupancy-based Cross-task Mutual Learning for 3D Scene Generation OccScene：基于语义占用的3D场景生成跨任务相互学习

IF 23.6 1区计算机科学

IEEE Transactions on Pattern Analysis and Machine Intelligence Pub Date : 2025-08-25 DOI: 10.1109/tpami.2025.3602511

Bohan Li, Xin Jin, Jianan Wang, Yukai Shi, Yasheng Sun, Xiaofeng Wang, Zhuang Ma, Baao Xie, Chao Ma, Xiaokang Yang, Wenjun Zeng

引用次数: 0

Planner3D: LLM-enhanced Graph Prior Meets 3D Indoor Scene Explicit Regularization Planner3D: llm增强的图先验满足3D室内场景显式正则化

IF 23.6 1区计算机科学

IEEE Transactions on Pattern Analysis and Machine Intelligence Pub Date : 2025-08-25 DOI: 10.1109/tpami.2025.3602216

Yao Wei, Martin Renqiang Min, George Vosselman, Li Erran Li, Michael Ying Yang

引用次数: 0

GPT4Point++: Advancing Unified Point-Language Understanding and Generation. gpt4point++：推进统一的点语言理解和生成。

IF 23.6 1区计算机科学

IEEE Transactions on Pattern Analysis and Machine Intelligence Pub Date : 2025-08-11 DOI: 10.1109/tpami.2025.3597938

Zhangyang Qi,Ye Fang,Zeyi Sun,Xiaoyang Wu,Tong Wu,Jiaqi Wang,Dahua Lin,Hengshuang Zhao

{"title":"GPT4Point++: Advancing Unified Point-Language Understanding and Generation.","authors":"Zhangyang Qi,Ye Fang,Zeyi Sun,Xiaoyang Wu,Tong Wu,Jiaqi Wang,Dahua Lin,Hengshuang Zhao","doi":"10.1109/tpami.2025.3597938","DOIUrl":"https://doi.org/10.1109/tpami.2025.3597938","url":null,"abstract":"Multimodal Large Language Models (MLLMs) have made significant progress in 2D image-text tasks, but the 3D domain remains challenging. To bridge this gap, we introduce GPT4Point and its enhanced version, GPT4Point++, both of which are pioneering point-language multimodal models designed for 3D object understanding and generation. They excel in tasks such as 3D object recognition, 3D point cloud captioning and question answering. Additionally, GPT4Point is equipped with advanced capabilities for controllable 3D generation, and it can get high-quality results through a low-quality point-text feature that maintains geometric shapes and colors. GPT4Point's training consists of two stages: first, aligning point-text features, followed by integrating the LLM. Our advanced version GPT4Point++ simplifies this with a single, unified end-to-end training approach for improved performance. To support the substantial demand for 3D object-text pairs, we have developed Capverse, a point-language dataset annotation engine. Capverse constructs a large-scale database with diverse levels of text granularity by leveraging the Objaverse dataset. We established a comprehensive benchmark to assess 3D point-language understanding. Extensive evaluations show that GPT4Point and GPT4Point++ excel in both understanding and generation tasks. Additionally, GPT4Point effectively evaluates 3D object generation methods and demonstrates strong understanding of both individual objects and indoor scenes, highlighting its robustness. 3D Multimodal Large Model, 3D Object Recognition, 3D Object Generation.","PeriodicalId":13426,"journal":{"name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","volume":"27 1","pages":""},"PeriodicalIF":23.6,"publicationDate":"2025-08-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144819923","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Guest Editorial: Introduction to the Special Section on Computational Photography 客座社论：计算机摄影专题导论

IF 23.6 1区计算机科学

IEEE Transactions on Pattern Analysis and Machine Intelligence Pub Date : 2025-08-06 DOI: 10.1109/tpami.2025.3584422

Boxin Shi, Ashok Veeraraghavan, Roarke Horstmeyer, Wolfgang Heidrich

引用次数: 0

GPHM: Gaussian Parametric Head Model for Monocular Head Avatar Reconstruction. 高斯参数头部模型用于单目头部图像重建。

IF 23.6 1区计算机科学

IEEE Transactions on Pattern Analysis and Machine Intelligence Pub Date : 2025-08-06 DOI: 10.1109/tpami.2025.3596331

Yuelang Xu,Zhaoqi Su,Qingyao Wu,Yebin Liu

{"title":"GPHM: Gaussian Parametric Head Model for Monocular Head Avatar Reconstruction.","authors":"Yuelang Xu,Zhaoqi Su,Qingyao Wu,Yebin Liu","doi":"10.1109/tpami.2025.3596331","DOIUrl":"https://doi.org/10.1109/tpami.2025.3596331","url":null,"abstract":"Creating high-fidelity 3D human head avatars is crucial for applications in VR/AR, digital human, and film production. Recent advances have leveraged morphable face models to generate animated head avatars from easily accessible data, representing varying identities and expressions within a low-dimensional parametric space. However, existing methods often struggle with modeling complex appearance details, e.g., hairstyles, and suffer from low rendering quality and efficiency. In this paper we introduce a novel approach, 3D Gaussian Parametric Head Model, which employs 3D Gaussians to accurately represent the complexities of the human head, allowing precise control over both identity and expression. The Gaussian model can handle intricate details, enabling realistic representations of varying appearances and complex expressions. Furthermore, we presents a well-designed training framework to ensure smooth convergence, providing a robust guarantee for learning the rich content. Our method achieves high-quality, photo-realistic rendering with real-time efficiency, making it a valuable contribution to the field of parametric head models. Finally, we apply the 3D Gaussian Parametric Head Model to monocular video or few-shot head avatar reconstruction tasks, which enables instant reconstruction of high-quality 3D head avatars even when input data is extremely limited, surpassing previous methods in terms of reconstruction quality and training speed. Project page: https://yuelangx.github.io/gphmv2/.","PeriodicalId":13426,"journal":{"name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","volume":"15 1","pages":""},"PeriodicalIF":23.6,"publicationDate":"2025-08-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144791898","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Stereo-Talker: Audio-driven 3D Human Synthesis with Prior-Guided Mixture-of-Experts 立体声扬声器：音频驱动的3D人类合成与先前引导的专家混合

IF 23.6 1区计算机科学

IEEE Transactions on Pattern Analysis and Machine Intelligence Pub Date : 2025-08-05 DOI: 10.1109/tpami.2025.3596160

Xiang Deng, Youxin Pang, Xiaochen Zhao, Chao Xu, Lizhen Wang, Hongjiang Xiao, Shi Yan, Hongwen Zhang, Yebin Liu

引用次数: 0

VolGen: Volumetric Latent Diffusion Models for 3D Object Generation. VolGen：三维物体生成的体积潜在扩散模型。

IF 23.6 1区计算机科学

IEEE Transactions on Pattern Analysis and Machine Intelligence Pub Date : 2025-08-04 DOI: 10.1109/tpami.2025.3594029

Jiaxiang Tang,Xiang Wen,Hao-Xiang Guo,Hao Jiang,Zhihang Li,Jing Xu,Gang Zeng

{"title":"VolGen: Volumetric Latent Diffusion Models for 3D Object Generation.","authors":"Jiaxiang Tang,Xiang Wen,Hao-Xiang Guo,Hao Jiang,Zhihang Li,Jing Xu,Gang Zeng","doi":"10.1109/tpami.2025.3594029","DOIUrl":"https://doi.org/10.1109/tpami.2025.3594029","url":null,"abstract":"We propose to extend 2D latent diffusion models, well known from the Stable-Diffusion series, to volumetric latent diffusion models for 3D object generation. Specifically, we first train a Volumetric Variational Auto-Encoder (VVAE) to compress 3D occupancy grids into a latent space, which compresses the $512^{3}$ occupancy grid into a $32^{3}$ latent code. We then train a diffusion model on this latent space, utilizing 3D convolutions and cross-attention layers for image conditioning. This Volumetric Latent Diffusion Model (VLDM) generates accurate and smooth mesh surfaces from single-view image inputs, and generalizes well to unseen domains during inference in around 10 seconds. Our key insight is that a simple volume-based latent diffusion model can also perform well for 3D generation tasks, without relying on sparse representations like point clouds or 3D specific techniques like triplane Neural Radiance Fields (NeRF). Extensive experiments demonstrate the effectiveness of our latent diffusion models in the 3D domain, indicating a promising direction for 3D generation tasks.","PeriodicalId":13426,"journal":{"name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","volume":"13 1","pages":""},"PeriodicalIF":23.6,"publicationDate":"2025-08-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144778168","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

GenPoly: Learning Generalized and Tessellated Shape Priors via 3D Polymorphic Evolving GenPoly：通过三维多态进化学习广义和镶嵌形状先验

IF 23.6 1区计算机科学

IEEE Transactions on Pattern Analysis and Machine Intelligence Pub Date : 2025-07-31 DOI: 10.1109/tpami.2025.3593807

Bangzhen Liu, Yuyang Yu, Xuemiao Xu, Cheng Xu, Chenxi Zheng, Haoxin Yang, Shaoyu Huang, Shengfeng He

引用次数: 0

GetMesh: A Controllable Model for High-quality Mesh Generation and Manipulation GetMesh：用于高质量网格生成和操作的可控模型

IF 23.6 1区计算机科学

IEEE Transactions on Pattern Analysis and Machine Intelligence Pub Date : 2025-07-31 DOI: 10.1109/tpami.2025.3594478

Ben Fei, Jinyi Wang, Lei Bai, Keyi Liu, Xudong Xu, Weidong Yang, Ya Zhang, Ying He, Dahua Lin, Zhaoyang Lyu, Bo Dai

引用次数: 0