Weihao Xia

Weihao Xia

Auto-generated profile, based on publicly available information

Weihao Xia

University of Cambridge

Research Focus & Metrics

Academic Career Length

8Years (2019-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
9 November 2023 in ACM Computing Surveys
Verified
Journal Article
Open access
WXWeihao Xia
Weihao Xia
JXJing-Hao Xue
Jing-Hao Xue
Recent years have seen remarkable progress in deep learning powered visual content creation. This includes deep generative 3D-aware image synthesis, which produces high-fidelity images in a 3D-consistent manner while simultaneously capturing compact surfaces of objects from pure image collections without the need for any 3D supervision, thus bridging the gap between 2D imagery and 3D reality. The field of computer vision has been recently captivated by the task of deep generative 3D-aware image synthesis, with hundreds of papers appearing in top-tier journals and conferences over the past few years (mainly the past two years), but there lacks a comprehensive survey of this remarkable and swift progress. Our survey aims to introduce new researchers to this topic, provide a useful reference for related works, and stimulate future research directions through our discussion section. Apart from the presented papers, we aim to constantly update the latest relevant papers along with corresponding implementations at https://weihaox.github.io/3D-aware-Gen .

29 September 2024
Verified
Book Chapter
Closed access
PDF file
WXWeihao Xia
Weihao Xia
RCRaoul de Charette
Raoul de Charette
COCengiz Oztireli
Cengiz Oztireli
JXJing-Hao Xue
Jing-Hao Xue


21 January 2025 in IEEE Transactions on Pattern Analysis and Machine Intelligence
Verified
Journal Article
Closed access
YLYong Liu
Yong Liu
RYRan Yu
Ran Yu
FYFei Yin
Fei Yin
XZXinyuan Zhao
Xinyuan Zhao
WZWei Zhao
Wei Zhao
YYYujiu Yang
Yujiu Yang
Recently, several spatial-temporal memory-based methods have verified that storing intermediate frames with masks as memory helps segment target objects in videos. However, they mainly focus on better matching between the current frame and memory frames without paying attention to the quality of the memory. Consequently, frames with poor segmentation masks may be memorized, leading to error accumulation problems. Besides, the linear increase of memory frames with the growth of frame numbers limits the ability of the models to handle long videos. To this end, we propose a Quality-aware Dynamic Memory Network (QDMN) to evaluate the segmentation quality of each frame, allowing the memory bank to selectively store accurately segmented frames and prevent error accumulation. Then, we combine the segmentation quality with temporal consistency to dynamically update the memory bank and make the models can handle videos of arbitrary length. The above operation ensures the reliability of memory frames and improves the quality of memory at the frame level. Moreover, we observe that the memory features extracted from reliable frames still contain noise and have limited representation capabilities. To address this problem, we propose to perform memory enhancement and anchoring on the basis of QDMN to improve the quality of memory from the feature level, resulting in a more robust and effective network QDMN++. Our method achieves state-of-the-art performance on all popular benchmarks. Moreover, extensive experiments demonstrate that the proposed memory screening mechanism can be applied to any memory-based methods as generic plugins.

4 November 2025 in IEEE Transactions on Circuits and Systems for Video Technology
Verified
Journal Article
Closed access
HWHai Wang
Hai Wang
XXXiaoyu Xiang
Xiaoyu Xiang
WXWeihao Xia
Weihao Xia
JXJing-Hao Xue
Jing-Hao Xue
The advent of text-driven 360-degree panorama generation, enabling the synthesis of 360-degree panoramic images directly from textual descriptions, marks a transformative advancement in immersive visual content creation. This innovation significantly simplifies the traditionally complex process of producing such content. Recent progress in text-to-image diffusion models has accelerated the rapid development in this emerging field. This survey presents a comprehensive review of text-driven 360-degree panorama generation, offering an in-depth analysis of state-of-the-art algorithms. We extend our analysis to two closely related domains: text-driven 360-degree 3D scene generation and text-driven 360-degree panoramic video generation. Furthermore, we critically examine current limitations and propose promising directions for future research. A curated project page with relevant resources and research papers is available at https://littlewhitesea.github.io/Text-Driven-Pano-Gen/.

22 March 2022 in arXiv
Verified
Preprint
Open access
PDF file
WXWeihao Xia
Weihao Xia
YZYulun Zhang
Yulun Zhang
YYYujiu Yang
Yujiu Yang
JXJing-Hao Xue
Jing-Hao Xue
BZBolei Zhou
Bolei Zhou
MYMing Yang
Ming Yang
GAN inversion aims to invert a given image back into the latent space of a pretrained GAN model, for the image to be faithfully reconstructed from the inverted code by the generator. As an emerging technique to bridge the real and fake image domains, GAN inversion plays an essential role in enabling the pretrained GAN models such as StyleGAN and BigGAN to be used for real image editing applications. Meanwhile, GAN inversion also provides insights on the interpretation of GAN's latent space and how the realistic images can be generated. In this paper, we provide an overview of GAN inversion with a focus on its recent algorithms and applications. We cover important techniques of GAN inversion and their applications to image restoration and image manipulation. We further elaborate on some trends and challenges for future directions.