Zixuan Wang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Zixuan Wang has a total of 36 co-authors. Here are the top co-authors by number of shared publications:
- Jia Jia
Department of Computer Science and Technology, BNRist, Tsinghua University, Beijing, China
6 shared publications - Xiaoyu Qin
Department of Computer Science and Technology, Tsinghua University, Beijing, China
5 shared publications - Shikun Sun
Tsinghua University, Beijing, China
4 shared publications - Jiayi Li
Department of Computer Science and Technology, Tsinghua University, Beijing, China
2 shared publications - Jiebo Luo
University of Rochester, Rochester, New York, USA
2 shared publications - Qixin Wang
Department of Computer Science and Technology, Tsinghua University, Beijing, China
2 shared publications
Latest Publications
- Open Access
- 19 July 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-12
UCM: Unified Modeling of Camera Control and Memory with Time-aware Positional Encoding Warping for World Models
- 19 July 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-12
Open AccessUCM: Unified Modeling of Camera Control and Memory with Time-aware Positional Encoding Warping for World Models
- Open Access
- 19 July 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-11
VFAvatar: Feed-Forward 3D Avatar Reconstruction from Casual Image Collections
The growing demand for personalized 3D avatars calls for efficient reconstruction methods from casual photos. This task remains challenging due to unconstrained viewpoints, partial body visibility, and temporal variations across input images. While some previous methods circumvent these difficulties by adopting generative approaches like score distillation, they struggle to preserve authentic appearance details from source images. To address these limitations, we introduce Visual-Fusion-Avatar (VFAvatar), a novel feed-forward framework that reconstructs 3D avatars by fusing visual cues in just a few seconds. VFAvatar couples a pose-free reconstruction foundation model with a pretrained human generation prior in a mutually reinforcing manner. And we propose a visibility-aware, view-attentive residual aggregation mechanism that routes and fuses per-view updates, allowing partial observations from different images to be assembled into a single coherent avatar. Experiments demonstrate that VFAvatar significantly outperforms state-of-the-art methods in both reconstruction fidelity and efficiency, while enabling shape and pose manipulation. Code is available on: https://github.com/huangshuo200823/VFAvatar.
- 19 July 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-11
Open AccessVFAvatar: Feed-Forward 3D Avatar Reconstruction from Casual Image Collections
The growing demand for personalized 3D avatars calls for efficient reconstruction methods from casual photos. This task remains challenging due to unconstrained viewpoints, partial body visibility, and temporal variations across input images. While some previous methods circumvent these difficulties by adopting generative approaches like score distillation, they struggle to preserve authentic appearance details from source images. To address these limitations, we introduce Visual-Fusion-Avatar (VFAvatar), a novel feed-forward framework that reconstructs 3D avatars by fusing visual cues in just a few seconds. VFAvatar couples a pose-free reconstruction foundation model with a pretrained human generation prior in a mutually reinforcing manner. And we propose a visibility-aware, view-attentive residual aggregation mechanism that routes and fuses per-view updates, allowing partial observations from different images to be assembled into a single coherent avatar. Experiments demonstrate that VFAvatar significantly outperforms state-of-the-art methods in both reconstruction fidelity and efficiency, while enabling shape and pose manipulation. Code is available on: https://github.com/huangshuo200823/VFAvatar.
- Open Access
- 27 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 6720-6729
HarmoniVox: Painting Voices to Match the Avatar's Soul
- 27 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 6720-6729
Open AccessHarmoniVox: Painting Voices to Match the Avatar's Soul
- Open Access
- 27 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 6840-6849
PP-Motion: Physical-Perceptual Fidelity Evaluation for Human Motion Generation
- 27 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 6840-6849
Open AccessPP-Motion: Physical-Perceptual Fidelity Evaluation for Human Motion Generation
- Open Access
- 27 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 10239-10247
DEPO: Enhancing E-commerce Image Background Generation with Short Trajectory Direct Expected Preference Optimization
- 27 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 10239-10247
Open AccessDEPO: Enhancing E-commerce Image Background Generation with Short Trajectory Direct Expected Preference Optimization
- Open Access
- 28 October 2024
- Published by Association for Computing Machinery (ACM)
- p. 10200-10209
DanceCamAnimator: Keyframe-Based Controllable 3D Dance Camera Synthesis
Synthesizing camera movements from music and dance is highly challenging due to the contradicting requirements and complexities of dance cinematography. Unlike human movements, which are always continuous, dance camera movements involve both continuous sequences of variable lengths and sudden drastic changes to simulate the switching of multiple cameras. However, in previous works, every camera frame is equally treated and this causes jittering and unavoidable smoothing in post-processing. To solve these problems, we propose to integrate animator dance cinematography knowledge by formulating this task as a three-stage process: keyframe detection, keyframe synthesis, and tween function prediction. Following this formulation, we design a novel end-to-end dance camera synthesis framework DanceCamAnimator, which imitates human animation procedures and shows powerful keyframe-based controllability with variable lengths. Extensive experiments on the DCM dataset demonstrate that our method surpasses previous baselines quantitatively and qualitatively. Code will be available at https://github.com/Carmenw1203/DanceCamAnimator-Official.
- 28 October 2024
- Published by Association for Computing Machinery (ACM)
- p. 10200-10209
Open AccessDanceCamAnimator: Keyframe-Based Controllable 3D Dance Camera Synthesis
Synthesizing camera movements from music and dance is highly challenging due to the contradicting requirements and complexities of dance cinematography. Unlike human movements, which are always continuous, dance camera movements involve both continuous sequences of variable lengths and sudden drastic changes to simulate the switching of multiple cameras. However, in previous works, every camera frame is equally treated and this causes jittering and unavoidable smoothing in post-processing. To solve these problems, we propose to integrate animator dance cinematography knowledge by formulating this task as a three-stage process: keyframe detection, keyframe synthesis, and tween function prediction. Following this formulation, we design a novel end-to-end dance camera synthesis framework DanceCamAnimator, which imitates human animation procedures and shows powerful keyframe-based controllability with variable lengths. Extensive experiments on the DCM dataset demonstrate that our method surpasses previous baselines quantitatively and qualitatively. Code will be available at https://github.com/Carmenw1203/DanceCamAnimator-Official.
- Open Access
- 28 October 2024
- Published by Association for Computing Machinery (ACM)
- p. 6880-6889
PlacidDreamer: Advancing Harmony in Text-to-3D Generation
Recently, text-to-3D generation has attracted significant attention, resulting in notable performance enhancements. Previous methods utilize end-to-end 3D generation models to initialize 3D Gaussians, multi-view diffusion models to enforce multi-view consistency, and text-to-image diffusion models to refine details with score distillation algorithms. However, these methods exhibit two limitations. Firstly, they encounter conflicts in generation directions since different models aim to produce diverse 3D assets. Secondly, the issue of over-saturation in score distillation has not been thoroughly investigated and solved. To address these limitations, we propose PlacidDreamer, a text-to-3D framework that harmonizes initialization, multi-view generation, and text-conditioned generation with a single multi-view diffusion model, while simultaneously employing a novel score distillation algorithm to achieve balanced saturation. To unify the generation direction, we introduce the Latent-Plane module, a training-friendly plug-in extension that enables multi-view diffusion models to provide fast geometry reconstruction for initialization and enhanced multi-view images to personalize the text-to-image diffusion model. To address the over-saturation problem, we propose to view score distillation as a multi-objective optimization problem and introduce the Balanced Score Distillation algorithm, which offers a Pareto Optimal solution that achieves both rich details and balanced saturation. Extensive experiments validate the outstanding capabilities of our PlacidDreamer. The code is available at https://github.com/HansenHuang0823/PlacidDreamer.
- 28 October 2024
- Published by Association for Computing Machinery (ACM)
- p. 6880-6889
Open AccessPlacidDreamer: Advancing Harmony in Text-to-3D Generation
Recently, text-to-3D generation has attracted significant attention, resulting in notable performance enhancements. Previous methods utilize end-to-end 3D generation models to initialize 3D Gaussians, multi-view diffusion models to enforce multi-view consistency, and text-to-image diffusion models to refine details with score distillation algorithms. However, these methods exhibit two limitations. Firstly, they encounter conflicts in generation directions since different models aim to produce diverse 3D assets. Secondly, the issue of over-saturation in score distillation has not been thoroughly investigated and solved. To address these limitations, we propose PlacidDreamer, a text-to-3D framework that harmonizes initialization, multi-view generation, and text-conditioned generation with a single multi-view diffusion model, while simultaneously employing a novel score distillation algorithm to achieve balanced saturation. To unify the generation direction, we introduce the Latent-Plane module, a training-friendly plug-in extension that enables multi-view diffusion models to provide fast geometry reconstruction for initialization and enhanced multi-view images to personalize the text-to-image diffusion model. To address the over-saturation problem, we propose to view score distillation as a multi-objective optimization problem and introduce the Balanced Score Distillation algorithm, which offers a Pareto Optimal solution that achieves both rich details and balanced saturation. Extensive experiments validate the outstanding capabilities of our PlacidDreamer. The code is available at https://github.com/HansenHuang0823/PlacidDreamer.
- Open Access
- 26 October 2023
- Published by Association for Computing Machinery (ACM)
- p. 9393-9395
HoloSinger: Semantics and Music Driven Motion Generation with Octahedral Holographic Projection
- 26 October 2023
- Published by Association for Computing Machinery (ACM)
- p. 9393-9395
Open AccessHoloSinger: Semantics and Music Driven Motion Generation with Octahedral Holographic Projection