Jionghao Wang

MTPano: Multi-Task Panoramic Scene Understanding via Label-Free Integration of Dense Prediction Priors

Jingdong Zhang, Xiaohang Zhan, Lingzhi Zhang, Yizhou Wang et autres

Comprehensive panoramic scene understanding is critical for immersive applications, yet it remains challenging due to the scarcity of high-resolution, multi-task annotations. While perspective foundation models have achieved success through data scaling, directly adapting them to the panoramic domain often fails due to …

us (code pays fourni par la source)

SPGen: Spherical Projection as Consistent and Flexible Representation for Single Image 3D Shape Generation

Jingdong Zhang, Weikai Chen, Jionghao Wang, Zhengming Yu et autres

Existing single-view 3D generative models typically adopt multiview diffusion priors to reconstruct object surfaces, yet they remain prone to inter-view inconsistencies and are unable to faithfully represent complex internal structure or nontrivial topologies. In particular, we encode geometry information by projecting it …

us, ru, hk (code pays fourni par la source)

PDT: Point Distribution Transformation with Diffusion Models

Jionghao Wang, Cheng Lin, Yuan Liu, Rui Xu et autres

Point-based representations have consistently played a vital role in geometric data structures. Most point cloud learning and processing methods typically leverage the unordered and unconstrained nature to represent the underlying geometry of 3D shapes. However, how to extract meaningful structural information from …

us, hk, cn (code pays fourni par la source)

Disentangled Clothed Avatar Generation from Text Descriptions

Jionghao Wang, Yuan Liu, Zhiyang Dou, Zhengming Yu et autres

cn, us, hk (code pays fourni par la source)

Real-Time Free Viewpoint Video Synthesis System Based on DIBR and a Depth Estimation Network

Shuai Guo, Jingchuan Hu, Kai Zhou, Jionghao Wang et autres

Depth image-based rendering (DIBR) view synthesis is the most widely employed method in real-time FVV research. Despite recent progress, most DIBR-based FVV synthesis approaches are not sufficiently simple and effective in filling holes and artifacts. Additionally, they use RGB-D cameras, which are …

cn (code pays fourni par la source)

Disentangled Clothed Avatar Generation from Text Descriptions

Jionghao Wang, Yuan Liu, Zhiyang Dou, Zhengming Yu et autres

In this paper, we introduce a novel text-to-avatar generation method that separately generates the human body and the clothes and allows high-quality animation on the generated avatar. While recent advancements in text-to-avatar generation have yielded diverse human avatars from text prompts, these …

360-Degree Panorama Generation from Few Unregistered NFoV Images

Jionghao Wang, Ziyu Chen, Jun Ling, Rong Xie et autres

360° panoramas are extensively utilized as environmental light sources in computer graphics. However, capturing a 360° × 180° panorama poses challenges due to the necessity of specialized and costly equipment, and additional human resources. Prior studies develop various learning-based generative methods to …

cn (code pays fourni par la source)

Efficient Human Rendering with Geometric and Semantic Priors

Jionghao Wang, Shuai Guo, Qiuwen Wang, Rong Xie et autres

Recently, human rendering has attracted many attention thanks to its vast applications. With new advances in neural rendering and radiance field, synthesizing realistic novel view images from multi-view camera images can be achived with less manual labour. However, due to the data-driven …

cn (code pays fourni par la source)

RGBD-based Real-time Volumetric Reconstruction System: Architecture Design and Implementation

Kai Zhou, Shuai Guo, Jingchuan Hu, Jionghao Wang et autres

With the increasing popularity of commercial depth cameras, 3D reconstruction of dynamic scenes has aroused widespread interest. Although many novel 3D applications have been unlocked, real-time performance is still a big problem. In this paper, a low-cost, real-time system: LiveRecon3D, is presented, …

cn (code pays fourni par la source)

A new free viewpoint video dataset and DIBR benchmark

Shuai Guo, Kai Zhou, Jingchuan Hu, Jionghao Wang et autres

Free viewpoint video (FVV) has drawn great attention in recent years, which provides viewers with strong interactive and immersive experience. Despite the developments made, further progress of FVV research is limited by existing datasets that mostly have too few number of camera …

cn (code pays fourni par la source)