WGWanshui Gan

Wanshui Gan

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Wanshui Gan has a total of 23 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    MegaParts: Scaling Part-Aware 3D Object Generation to 300 Parts via Token-Efficient Autoregressive Modeling

    by Manwen Liao, Xinyu Lian, Jian Mao, Kaixu Chen, Li Luo, Jinghao Yan, Wanshui Gan, Qiao Yu, Weitian Zhang, Chunhua Shen, et al.

  • Zero-Shot Text-Driven Dynamic Neural Radiance Fields Stylization

    by Wanlin Liang, Hongbin Xu, Wanshui Gan, Wenxiong Kang

    Text-driven style transfer for Neural Radiance Fields (NeRFs) is an emerging research topic that leverages text descriptions instead of reference style images to apply style transfer. However, existing methods for stylizing NeRFs predominantly struggle to extend to 4D dynamic scenes, due to NeRFs' inherent limitation to static environments. Moreover, these current methods require training for each specific text input, which limits them to a single style description and significantly hampers generalizability and applications. In this paper, we introduce a novel approach to zero-shot text-driven 4D style transfer that adopts text inputs into the CLIP's style space with a canonical feature volume. Specifically, using geometric priors from pre-trained dynamic Neural Radiance Fields, we train a canonical feature volume by rendering feature maps under the supervision of a pre-trained VGG encoder. Then we utilize CLIP's multi-modal embedding to connect the text descriptions with style images and learn a canonical style transformation matrix in CLIP's feature space. Experiments show that our method achieves zero-shot text-driven style transfer for dynamic neural radiance fields and maintains good multi-view and cross-time consistency.


  • A Comprehensive Framework for 3D Occupancy Estimation in Autonomous Driving

    by Wanshui Gan, Ningkai Mo, Hongbin Xu, Naoto Yokoya

    3D occupancy estimation from surrounding-view images is an exciting task in autonomous driving, following the success of Bird's Eye View (BEV) perception. In this work, we present a comprehensive framework for 3D occupancy estimation, which reveals several key components for 3D occupancy estimation, such as network design, optimization, and evaluation. In addition, we explore the relationship between 3D occupancy estimation and other related tasks, such as monocular depth estimation and 3D reconstruction, which could advance the study of 3D perception in autonomous driving. For evaluation, we propose a simple sampling strategy to define the metric for occupancy evaluation, which is flexible for current public datasets. Moreover, we establish a benchmark in terms of the depth estimation metric, where we compare our proposed method with monocular depth estimation methods on the DDAD and Nuscenes datasets and achieve competitive performance. The relevant code is available in https://github.com/GANWANSHUI/SimpleOccupancy .


  • V4D: Voxel for 4D Novel View Synthesis

    by Wanshui Gan, Hongbin Xu, Yi Huang, Shifeng Chen, Naoto Yokoya

    Neural radiance fields have made a remarkable breakthrough in the novel view synthesis task at the 3D static scene. However, for the 4D circumstance (e.g., dynamic scene), the performance of the existing method is still limited by the capacity of the neural network, typically in a multilayer perceptron network (MLP). In this article, we utilize 3D Voxel to model the 4D neural radiance field, short as V4D, where the 3D voxel has two formats. The first one is to regularly model the 3D space and then use the sampled local 3D feature with the time index to model the density field and the texture field by a tiny MLP. The second one is in look-up tables (LUTs) format that is for the pixel-level refinement, where the pseudo-surface produced by the volume rendering is utilized as the guidance information to learn a 2D pixel-level refinement mapping. The proposed LUTs-based refinement module achieves the performance gain with little computational cost and could serve as the plug-and-play module in the novel view synthesis task. Moreover, we propose a more effective conditional positional encoding toward the 4D data that achieves performance gain with negligible computational burdens. Extensive experiments demonstrate that the proposed method achieves state-of-the-art performance at a low computational cost.


  • Rethinking 3D cost aggregation in stereo matching

    by Wanshui Gan, Wenhao Wu, Shifeng Chen, Yuxiang Zhao, Pak Kin Wong