1,035 Hits in 7.5 sec

A Shading-Guided Generative Implicit Model for Shape-Accurate 3D-Aware Image Synthesis [article]

Xingang Pan, Xudong Xu, Chen Change Loy, Christian Theobalt, Bo Dai
2021 arXiv   pre-print
In this work, we address this ambiguity by proposing a novel shading-guided generative implicit model that is able to learn a starkly improved shape representation.  ...  The advancement of generative radiance fields has pushed the boundary of 3D-aware image synthesis.  ...  Chan for sharing the codebase of pi-GAN. This study is supported under the ERC Consolidator Grant 4DRepLy (770784).  ... 
arXiv:2110.15678v3 fatcat:4pduubi7xvdurj3dwxssxhzxbq

AvatarCLIP: Zero-Shot Text-Driven Generation and Animation of 3D Avatars [article]

Fangzhou Hong, Mingyuan Zhang, Liang Pan, Zhongang Cai, Lei Yang, Ziwei Liu
2022 arXiv   pre-print
Moreover, by leveraging the priors learned in the motion VAE, a CLIP-guided reference-based motion synthesis method is proposed for the animation of the generated 3D avatar.  ...  Based on the generated 3D human shapes, a volume rendering model is utilized to further facilitate geometry sculpting and texture generation.  ...  occlusion-aware, so that the optimization on multi-view images can lead to the accurate learning of a SDF representation.  ... 
arXiv:2205.08535v1 fatcat:ybbcbmjs2fckljkkx3pqgymejy

VoLux-GAN: A Generative Model for 3D Face Synthesis with HDRI Relighting [article]

Feitong Tan, Sean Fanello, Abhimitra Meka, Sergio Orts-Escolano, Danhang Tang, Rohit Pandey, Jonathan Taylor, Ping Tan, Yinda Zhang
2022 arXiv   pre-print
We propose VoLux-GAN, a generative framework to synthesize 3D-aware faces with convincing relighting.  ...  Multiple experiments and comparisons with other generative frameworks show how our model is a step forward towards photorealistic relightable 3D generative models.  ...  In this work, we propose a 3D aware generative model with HDRI relighting supervised by adversarial losses.  ... 
arXiv:2201.04873v1 fatcat:hkxwjzghvzanhgtw7vardumrqe

Generalizable Neural Performer: Learning Robust Radiance Fields for Human Novel View Synthesis [article]

Wei Cheng, Su Xu, Jingtan Piao, Chen Qian, Wayne Wu, Kwan-Yee Lin, Hongsheng Li
2022 arXiv   pre-print
We first introduce an Implicit Geometric Body Embedding strategy to enhance the robustness based on both parametric 3D human body model and multi-view images hints.  ...  This work targets at using a general deep learning framework to synthesize free-viewpoint images of arbitrary human performers, only requiring a sparse number of camera views as inputs and skirting per-case  ...  In this work, we focus on improving the generalization and robustness in free-viewpoint synthesis for arbitrary human performers from a sparse set of multi-view images.  ... 
arXiv:2204.11798v1 fatcat:xtfongmzfnedvirz4mplwp2api

Self-Supervised 2D Image to 3D Shape Translation with Disentangled Representations [article]

Berk Kaya, Radu Timofte
2021 arXiv   pre-print
for shape, appearance and viewpoint; and (iii) generating a realistic RGB image from these independent factors.  ...  We present a framework to translate between 2D image views and 3D object shapes. Recent progress in deep learning enabled us to learn structure-aware representations from a scene.  ...  Generative Models Apart from 3D reconstruction, our method also generates natural 2D images from 3D shapes.  ... 
arXiv:2003.10016v2 fatcat:vprjuqd4bje67dho2ybbh6n7oi

Smart Fashion: A Review of AI Applications in the Fashion Apparel Industry [article]

Seyed Omid Mohammadi, Ahmad Kalhor
2021 arXiv   pre-print
For each task, a time chart is provided to analyze the progress through the years.  ...  Furthermore, we provide a list of 86 public fashion datasets accompanied by a list of suggested applications and additional information for each.  ...  For example, "Image-3D Body" shows a system that generates 3D body models from 2D images.  ... 
arXiv:2111.00905v2 fatcat:6n6d62lntjfu5pxmjzgi4mpv6i

2021 Index IEEE Transactions on Image Processing Vol. 30

2021 IEEE Transactions on Image Processing  
The Author Index contains the primary entry for each item, listed under the first author's name.  ...  Model-Guided Deep Hyperspectral Image Super-Resolution. Dong, W., +, Progressive Diversified Augmentation for General Robustness of DNNs: A spectral Image Super-Resolution.  ...  ., +, TIP 2021 3676-3690 Rethinking Shape From Shading for Spoofing Detection. Di Martino, J.M., +, TIP 2021 1086-1099 Rethinking the U-Shape Structure for Salient Object Detection.  ... 
doi:10.1109/tip.2022.3142569 fatcat:z26yhwuecbgrnb2czhwjlf73qu

State of the Art on Neural Rendering [article]

Ayush Tewari, Ohad Fried, Justus Thies, Vincent Sitzmann, Stephen Lombardi, Kalyan Sunkavalli, Ricardo Martin-Brualla, Tomas Simon, Jason Saragih, Matthias Nießner, Rohit Pandey, Sean Fanello (+7 others)
2020 arXiv   pre-print
Concurrently, progress in computer vision and machine learning have given rise to a new approach to image synthesis and editing, namely deep generative models.  ...  However, the automatic generation of shape, materials, lighting, and other aspects of scenes remains a challenging problem that, if solved, would make photo-realistic computer graphics more widely accessible  ...  Visual Object Networks (VONs) [ZZZ * 18] is a 3D-aware generative model for synthesizing the appearance of objects with a disentangled 3D representation.  ... 
arXiv:2004.03805v1 fatcat:6qs7ddftkfbotdlfd4ks7llovq

GIRAFFE HD: A High-Resolution 3D-aware Generative Model [article]

Yang Xue, Yuheng Li, Krishna Kumar Singh, Yong Jae Lee
2022 arXiv   pre-print
3D-aware generative models have shown that the introduction of 3D information can lead to more controllable image generation.  ...  We propose GIRAFFE HD, a high-resolution 3D-aware generative model that inherits all of GIRAFFE's controllable features while generating high-quality, high-resolution images (512^2 resolution and above  ...  This work was supported in part by a Sony Focused Research Award and NSF CAREER IIS-2150012. We thank the anonymous reviewers for their constructive comments.  ... 
arXiv:2203.14954v1 fatcat:km6g3ul5hjfjdj5lnt5fawsnwm

PIFuHD: Multi-Level Pixel-Aligned Implicit Function for High-Resolution 3D Human Digitization [article]

Shunsuke Saito, Tomas Simon, Jason Saragih, Hanbyul Joo
2020 arXiv   pre-print
Recent advances in image-based 3D human shape estimation have been driven by the significant improvement in representation power afforded by deep neural networks.  ...  as a result.  ...  The 3D reconstruction is then guided by these maps to infer a particular 3D geometry, making it easier for the MLPs to produce details.  ... 
arXiv:2004.00452v1 fatcat:yf63rox7hbfqpfvtrjxfawe5qq

PIFu: Pixel-Aligned Implicit Function for High-Resolution Clothed Human Digitization [article]

Shunsuke Saito, Zeng Huang, Ryota Natsume, Shigeo Morishima, Angjoo Kanazawa, Hao Li
2019 arXiv   pre-print
We introduce Pixel-aligned Implicit Function (PIFu), a highly effective implicit representation that locally aligns pixels of 2D images with the global context of their corresponding 3D object.  ...  Using PIFu, we propose an end-to-end deep learning method for digitizing highly detailed clothed humans that can infer both 3D surface and texture from a single image, and optionally, multiple input images  ...  Recent 3D deep learning advances have shown that general shapes can be inferred from very few images and sometimes even a single input.  ... 
arXiv:1905.05172v3 fatcat:aq7mo4wt6nea5cpka24azjswba

VR content creation and exploration with deep learning: A survey

Miao Wang, Xu-Quan Lyu, Yi-Jun Li, Fang-Lue Zhang
2020 Computational Visual Media  
employed, designed specifically to handle panoramic images and video and virtual 3D scenes.  ...  VR content creation and exploration relates to image and video analysis, synthesis and editing, so deep learning methods such as fully convolutional networks and general adversarial networks are widely  ...  Fang-Lue Zhang was supported by a Victoria Early-Career Research Excellence Award.  ... 
doi:10.1007/s41095-020-0162-z fatcat:lgogzx26bvhn5f7uyefjkz7zny

Differentiable Rendering: A Survey [article]

Hiroharu Kato, Deniz Beker, Mihai Morariu, Takahiro Ando, Toru Matsuoka, Wadim Kehl, Adrien Gaidon
2020 arXiv   pre-print
Differentiable rendering is a novel field which allows the gradients of 3D objects to be calculated and propagated through images.  ...  Despite their success, they generally lack the understanding of 3D objects which form the image, as it is not always possible to collect 3D information about the scene or to easily annotate it.  ...  We would like to thank the PyTorch3D developers for their insightful comments and suggestions.  ... 
arXiv:2006.12057v2 fatcat:6zj6besdcnebrb4qww4u4jusji

Function4D: Real-time Human Volumetric Capture from Very Sparse Consumer RGBD Sensors [article]

Tao Yu, Zerong Zheng, Kaiwen Guo, Pengpeng Liu, Qionghai Dai, Yebin Liu
2021 arXiv   pre-print
Moreover, for detailed and complete surface generation, we propose detail-preserving deep implicit functions for RGBD input which can not only preserve the geometric details on the depth inputs but also  ...  In this paper, we propose a human volumetric capture method that combines temporal volumetric fusion and deep implicit functions.  ...  Methods in [59, 1] proposed to deform a parametric body model to fit the image observations including keypoints, silhouettes, and shading.  ... 
arXiv:2105.01859v2 fatcat:e7atvbmzqrbs3jbhyflkdpscdq

Text2Mesh: Text-Driven Neural Stylization for Meshes [article]

Oscar Michel, Roi Bar-On, Richard Liu, Sagie Benaim, Rana Hanocka
2021 arXiv   pre-print
Text2Mesh requires neither a pre-trained generative model nor a specialized 3D mesh dataset.  ...  In this work, we develop intuitive controls for editing the style of 3D objects.  ...  Taming faces has been guided by 3D shape analysis techniques (as transformers for high-resolution image synthesis, 2020. in [60]).  ... 
arXiv:2112.03221v1 fatcat:2mfgjh37lna5hnjj6pvms6zuey
« Previous Showing results 1 — 15 out of 1,035 results