相关参考文献
注意：仅列出部分参考文献，下载原文获取全部文献信息。
Article
Computer Science, Software Engineering
Stephen Lombardi et al.
Summary: MVP combines the completeness of volumetric representations with the efficiency of primitive-based rendering, achieving spatially shared computation through a convolutional architecture and minimizing computation in empty regions of space by moving volumetric primitives to cover only occupied areas. Its parameterization supports correspondence and tracking constraints and is robust even in areas where classical tracking fails, producing superior results in terms of quality and runtime performance compared to state-of-the-art methods.
ACM TRANSACTIONS ON GRAPHICS
(2021)
Proceedings Paper
Computer Science, Artificial Intelligence
Jiawei Wang et al.
Summary: This paper proposes a recurrent attention network (SaliencyBERT) for target-oriented multimodal sentiment classification. The model combines textual and visual information, utilizes a recurrent attention mechanism to capture target-sensitive visual representations, and achieves good performance results.
PATTERN RECOGNITION AND COMPUTER VISION,, PT III
(2021)
Proceedings Paper
Computer Science, Artificial Intelligence
Jiteng Mu et al.
Summary: Recent work has focused on using implicit functions for 3D shape reconstruction, with less attention on modeling articulated objects. The Articulated Signed Distance Functions (A-SDF) is introduced to represent articulated shapes with disentangled codes for shape and articulation, showing the ability to control joint angles and generalize well to unseen data.
2021 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2021)
(2021)
Proceedings Paper
Computer Science, Artificial Intelligence
Pablo Palafox et al.
Summary: Neural Parametric Models (NPMs) provide a learned alternative to traditional parametric 3D models, offering a more accurate and detailed representation of observed deformable sequences without the need for handcrafted constraints. By disentangling shape and pose into latent-space representations, NPMs enable optimization and outperform both parametric and non-parametric approaches in reconstruction and tracking tasks.
2021 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2021)
(2021)
Proceedings Paper
Computer Science, Artificial Intelligence
Edgar Tretschk et al.
Summary: NR-NeRF is a reconstruction and novel view synthesis approach for non-rigid dynamic scenes, allowing sophisticated renderings to be generated from novel virtual camera views using a single consumer-grade camera, without explicit supervision during training, resulting in stable outcomes.
2021 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2021)
(2021)
Proceedings Paper
Computer Science, Artificial Intelligence
Alex Trevithick et al.
Summary: The translation introduces a neural network that represents and renders 3D objects and scenes from 2D observations. Key to the approach is learning local features for each pixel and projecting them to 3D points, resulting in high-quality and realistic novel views.
2021 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2021)
(2021)
Proceedings Paper
Computer Science, Artificial Intelligence
Yijia Weng et al.
Summary: In this paper, we introduce a unified framework for category-level online pose tracking of objects from point cloud sequences. The proposed framework is capable of handling pose tracking for both rigid object instances and articulated objects through a novel end-to-end pipeline, achieving state-of-the-art performance on benchmark datasets.
2021 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2021)
(2021)
Proceedings Paper
Computer Science, Artificial Intelligence
Yilun Du et al.
Summary: The method utilizes Neural Radiance Flow (NeRFlow) to learn a 4D spatial-temporal representation of dynamic scenes from RGB images. By using a neural implicit representation, it captures 3D occupancy, radiance, and dynamics of scenes, enabling multi-view rendering and video processing tasks without additional supervision.
2021 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2021)
(2021)
Proceedings Paper
Computer Science, Artificial Intelligence
Christopher Xie et al.
Summary: In this research, a method for learning high-quality 3D object category models using the Neural Radiance Fields (NeRF) model is proposed. This method effectively separates foreground objects from backgrounds and achieves scene explanation through a two-component NeRF model. The results demonstrate convincing 3D object category modeling that exceeds existing methods.
2021 INTERNATIONAL CONFERENCE ON 3D VISION (3DV 2021)
(2021)
Proceedings Paper
Automation & Control Systems
Ajinkya Jain et al.
Summary: ScrewNet is a novel approach that estimates an object's articulation model directly from depth images without requiring a priori knowledge of the articulation model category.
2021 IEEE INTERNATIONAL CONFERENCE ON ROBOTICS AND AUTOMATION (ICRA 2021)
(2021)
Proceedings Paper
Computer Science, Artificial Intelligence
Aljaz Bozic et al.
Summary: The paper introduces a globally-consistent method for non-rigid object deformation tracking and 3D reconstruction using Neural Deformation Graphs modeled via a deep neural network. By optimizing the neural graph and object geometry with self-supervised learning, the approach shows significant improvements in both reconstruction and tracking performance compared to existing methods. The code for this approach is publicly available.
2021 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, CVPR 2021
(2021)
Proceedings Paper
Computer Science, Artificial Intelligence
Guy Gafni et al.
Summary: Dynamic neural radiance fields are introduced for modeling appearance and dynamics of a human face, utilizing an implicit representation based on scene representation networks and combining with a low-dimensional morphable model to handle facial dynamics. The volumetric representation allows for photorealistic image generation surpassing current video-based reenactment methods.
2021 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, CVPR 2021
(2021)
Proceedings Paper
Computer Science, Artificial Intelligence
Marko Mihajlovic et al.
Summary: Modeling rigid 3D objects using deep implicit representations has seen substantial progress, but extending these methods to human shape modeling is still in its infancy. The key challenge is learning a representation that can generalize body shape deformations for unseen subjects in unseen poses. LEAP is introduced as a novel neural occupancy representation of the human body, which greatly improves generalization capability and outperforms existing solutions.
2021 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, CVPR 2021
(2021)
Proceedings Paper
Computer Science, Artificial Intelligence
Gengshan Yang et al.
Summary: A template-free approach is introduced to learn 3D shapes from a single video, allowing faithful reconstruction of nonrigid 3D structures without specific category shape templates.
2021 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, CVPR 2021
(2021)
Proceedings Paper
Computer Science, Artificial Intelligence
Yang Li et al.
2020 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR)
(2020)
Article
Computer Science, Software Engineering
Stephen Lombardi et al.
ACM TRANSACTIONS ON GRAPHICS
(2019)
Proceedings Paper
Computer Science, Artificial Intelligence
Miroslava Slavcheva et al.
2018 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR)
(2018)
Proceedings Paper
Computer Science, Artificial Intelligence
Miroslava Slavcheva et al.
30TH IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2017)
(2017)
Article
Computer Science, Software Engineering
Javier Romero et al.
ACM TRANSACTIONS ON GRAPHICS
(2017)
Article
Computer Science, Software Engineering
Matthew Loper et al.
ACM TRANSACTIONS ON GRAPHICS
(2015)
