English
Related papers

Related papers: Make Encoder Great Again in 3D GAN Inversion throu…

200 papers

Head-mounted displays (HMDs) are essential for experiencing extended reality (XR) environments and observing virtual content. However, they obscure the upper part of the user's face, complicating external video recording and significantly…

Computer Vision and Pattern Recognition · Computer Science 2025-08-19 Fatemeh Ghorbani Lohesara , Karen Eguiazarian , Sebastian Knorr

Image inpainting seeks a semantically consistent way to recover the corrupted image in the light of its unmasked content. Previous approaches usually reuse the well-trained GAN as effective prior to generate realistic patches for missing…

Computer Vision and Pattern Recognition · Computer Science 2022-08-26 Yongsheng Yu , Libo Zhang , Heng Fan , Tiejian Luo

Scanpath prediction in 360{\deg} images can help realize rapid rendering and better user interaction in Virtual/Augmented Reality applications. However, existing scanpath prediction models for 360{\deg} images execute scanpath prediction on…

Computer Vision and Pattern Recognition · Computer Science 2024-07-16 Rong Quan , Yantao Lai , Mengyu Qiu , Dong Liang

Encoding information from 2D views of an object into a 3D representation is crucial for generalized 3D feature extraction. Such features can then enable 3D reconstruction, 3D generation, and other applications. We propose GOEmbed (Gradient…

Computer Vision and Pattern Recognition · Computer Science 2024-07-16 Animesh Karnewar , Roman Shapovalov , Tom Monnier , Andrea Vedaldi , Niloy J. Mitra , David Novotny

Recent advances in convolutional neural networks have shown promising results in 3D shape completion. But due to GPU memory limitations, these methods can only produce low-resolution outputs. To inpaint 3D models with semantic plausibility…

Computer Vision and Pattern Recognition · Computer Science 2017-11-20 Weiyue Wang , Qiangui Huang , Suya You , Chao Yang , Ulrich Neumann

Recently, deep learning-based 3D face reconstruction methods have demonstrated promising advancements in terms of quality and efficiency. Nevertheless, these techniques face challenges in effectively handling occluded scenes and fail to…

Computer Vision and Pattern Recognition · Computer Science 2025-03-18 Dapeng Zhao

We introduce VIVE3D, a novel approach that extends the capabilities of image-based 3D GANs to video editing and is able to represent the input video in an identity-preserving and temporally consistent way. We propose two new building…

Computer Vision and Pattern Recognition · Computer Science 2023-03-29 Anna Frühstück , Nikolaos Sarafianos , Yuanlu Xu , Peter Wonka , Tony Tung

Current 3D GAN inversion methods for human heads typically use only one single frontal image to reconstruct the whole 3D head model. This leaves out meaningful information when multi-view data or dynamic videos are available. Our method…

Computer Vision and Pattern Recognition · Computer Science 2023-12-12 Florian Barthel , Anna Hilsmann , Peter Eisert

Large kernel convolutions offer a scalable alternative to vision transformers for high-resolution 3D volumetric analysis, yet naively increasing kernel size often leads to optimization instability. Motivated by the spatial bias inherent in…

Computer Vision and Pattern Recognition · Computer Science 2026-02-02 Ho Hin Lee , Quan Liu , Shunxing Bao , Yuankai Huo , Bennett A. Landman

The current GAN inversion methods typically can only edit the appearance and shape of a single object and background while overlooking spatial information. In this work, we propose a 3D editing framework, 3D-GOI, to enable multifaceted…

Computer Vision and Pattern Recognition · Computer Science 2024-07-24 Haoran Li , Long Ma , Haolin Shi , Yanbin Hao , Yong Liao , Lechao Cheng , Pengyuan Zhou

The introduction of multiple viewpoints in video scenes inevitably increases the bitrates required for storage and transmission. To reduce bitrates, researchers have developed methods to skip intermediate viewpoints during compression and…

Image and Video Processing · Electrical Eng. & Systems 2023-05-08 Chengdong Lan , Hao Yan , Cheng Luo , Tiesong Zhao

To edit a real photo using Generative Adversarial Networks (GANs), we need a GAN inversion algorithm to identify the latent vector that perfectly reproduces it. Unfortunately, whereas existing inversion algorithms can synthesize images…

Computer Vision and Pattern Recognition · Computer Science 2022-02-25 Qianli Feng , Viraj Shah , Raghudeep Gadde , Pietro Perona , Aleix Martinez

Image composition is a complex task which requires a lot of information about the scene for an accurate and realistic composition, such as perspective, lighting, shadows, occlusions, and object interactions. Previous methods have…

Computer Vision and Pattern Recognition · Computer Science 2024-07-17 Amr Ghoneim , Jiju Poovvancheri , Yasushi Akiyama , Dong Chen

3D-aware Generative Adversarial Networks (GANs) have shown remarkable progress in learning to generate multi-view-consistent images and 3D geometries of scenes from collections of 2D images via neural volume rendering. Yet, the significant…

Computer Vision and Pattern Recognition · Computer Science 2024-01-05 Alex Trevithick , Matthew Chan , Towaki Takikawa , Umar Iqbal , Shalini De Mello , Manmohan Chandraker , Ravi Ramamoorthi , Koki Nagano

Recent advances in generative adversarial networks (GANs) have achieved great success in automated image composition that generates new images by embedding interested foreground objects into background images automatically. On the other…

Computer Vision and Pattern Recognition · Computer Science 2023-04-25 Changgong Zhang , Fangneng Zhan , Shijian Lu , Feiying Ma , Xuansong Xie

Effective robotic manipulation relies on a precise understanding of 3D scene geometry, and one of the most straightforward ways to acquire such geometry is through multi-view observations. Motivated by this, we present GP3 -- a 3D…

Robotics · Computer Science 2025-09-22 Quanhao Qian , Guoyang Zhao , Gongjie Zhang , Jiuniu Wang , Ran Xu , Junlong Gao , Deli Zhao

Training model to generate data has increasingly attracted research attention and become important in modern world applications. We propose in this paper a new geometry-based optimization approach to address this problem. Orthogonal to…

Machine Learning · Computer Science 2017-08-18 Trung Le , Hung Vu , Tu Dinh Nguyen , Dinh Phung

Three-dimensional (3D) shape measurement devices and techniques are being rapidly adopted within a variety of industries and applications. As acquiring 3D range data becomes faster and more accurate it becomes more challenging to…

Image and Video Processing · Electrical Eng. & Systems 2020-11-19 Matthew G. Finley , Tyler Bell

Implicit neural representations have emerged as a powerful tool in learning 3D geometry, offering unparalleled advantages over conventional representations like mesh-based methods. A common type of INR implicitly encodes a shape's boundary…

Computer Vision and Pattern Recognition · Computer Science 2024-10-17 Shen Fan , Przemyslaw Musialski

Generation of photo-realistic images, semantic editing and representation learning are a few of many potential applications of high resolution generative models. Recent progress in GANs have established them as an excellent choice for such…

Computer Vision and Pattern Recognition · Computer Science 2021-12-13 Partha Ghosh , Dominik Zietlow , Michael J. Black , Larry S. Davis , Xiaochen Hu