Tongji University
Shanghai Innovation InstituteA bicolor cat is a cat with white fur combined with fur of some other colour, for example solid black, tabby, or colourpointed.
There are various patterns of a bicolour cat. These range from the Van-patterned (colour on the crown of the head and the tail only) to a solid colour with a throat locket or medallion. Bicolour coats are found in many cat breeds, as well as being common in domestic longhair and domestic shorthair cats.
Warning
Problem: The current name of your GitHub Pages repository ("Solution: Please consider renaming the repository to "
http://".
However, if the current repository name is intended, you can ignore this message by removing "{% include widgets/debug_repo_name.html %}" in index.html.
Action required
Problem: The current root path of this site is "baseurl ("_config.yml.
Solution: Please set the
baseurl in _config.yml to "Education
-
Shanghai Innovation InstituteComputer Science & Artificial Intelligence
Ph.D. StudentMar. 2026 - present -
Tongji UniversityIntelligent Science and Technology
Ph.D. StudentMar. 2026 - present -
University of Southern CaliforniaAnalytics
M.S. StudentAug. 2021 - May. 2023
News
Selected Publications (view all )
FastAvatar: Towards Unified and Fast 3D Avatar Reconstruction with Large Gaussian Reconstruction Transformers
Yue Wu, Xuanhong Chen, Yufan Wu, Wen Li, Yuxi Lu, Kairui Feng
International Conference on Learning Representations (ICLR) 2026
Despite significant progress in 3D avatar reconstruction, it still faces challenges such as high time complexity, sensitivity to data quality, and low data utilization. We propose FastAvatar, a feedforward 3D avatar framework capable of flexibly leveraging diverse daily recordings (e.g., a single image, multi-view observations, or monocular video) to reconstruct a high-quality 3D Gaussian Splatting (3DGS) model within seconds, using only a single unified model. The core of FastAvatar is a Large Gaussian Reconstruction Transformer (LGRT) featuring three key designs: First, a 3DGS transformer aggregating multi-frame cues while injecting initial 3D prompt to predict the corresponding registered canonical 3DGS representations; Second, multi-granular guidance encoding (camera pose, expression coefficient, head pose) mitigating animation-induced misalignment for variable-length inputs; Third, incremental Gaussian aggregation via landmark tracking and sliced fusion losses. Integrating these features, FastAvatar enables incremental reconstruction, i.e., improving quality with more observations without wasting input data as in previous works. This yields a quality-speed-tunable paradigm for highly usable 3D avatar modeling. Extensive experiments show that FastAvatar has a higher quality and highly competitive speed compared to existing methods.
FastAvatar: Towards Unified and Fast 3D Avatar Reconstruction with Large Gaussian Reconstruction Transformers
Yue Wu, Xuanhong Chen, Yufan Wu, Wen Li, Yuxi Lu, Kairui Feng
International Conference on Learning Representations (ICLR) 2026
Despite significant progress in 3D avatar reconstruction, it still faces challenges such as high time complexity, sensitivity to data quality, and low data utilization. We propose FastAvatar, a feedforward 3D avatar framework capable of flexibly leveraging diverse daily recordings (e.g., a single image, multi-view observations, or monocular video) to reconstruct a high-quality 3D Gaussian Splatting (3DGS) model within seconds, using only a single unified model. The core of FastAvatar is a Large Gaussian Reconstruction Transformer (LGRT) featuring three key designs: First, a 3DGS transformer aggregating multi-frame cues while injecting initial 3D prompt to predict the corresponding registered canonical 3DGS representations; Second, multi-granular guidance encoding (camera pose, expression coefficient, head pose) mitigating animation-induced misalignment for variable-length inputs; Third, incremental Gaussian aggregation via landmark tracking and sliced fusion losses. Integrating these features, FastAvatar enables incremental reconstruction, i.e., improving quality with more observations without wasting input data as in previous works. This yields a quality-speed-tunable paradigm for highly usable 3D avatar modeling. Extensive experiments show that FastAvatar has a higher quality and highly competitive speed compared to existing methods.