Publications

(2024). Wonderland: Navigating 3D Scenes from a Single Image. arXiv'24.

Preprint Project

(2024). Omni-ID: Holistic Identity Representation Designed for Generative Tasks. arXiv'24.

Preprint Project

(2024). AC3D: Analyzing and Improving 3D Camera Control in Video Diffusion Transformers. arXiv'24.

Preprint Project

(2024). AToM: Amortized Text-to-Mesh using 2D Diffusion. arXiv'24.

Preprint Code Project

(2024). Magic123: One Image to High-Quality 3D Object Generation Using Both 2D and 3D Diffusion Priors. ICLR'24.

Preprint Code Project

(2023). Pix4Point: Image Pretrained Standard Transformers for 3D Point Cloud Understanding. 3DV'24.

Preprint Code

(2023). Exploring Open-Vocabulary Semantic Segmentation from CLIP Vision Encoder Distillation Only. ICCV'23.

Preprint Code

(2022). PointNeXt: Revisiting PointNet++ with Improved Training and Scaling Strategies. NeurIPS'22.

Preprint Code

(2022). Rethinking Learning-based Demosaicing, Denoising, and Super-Resolution Pipeline. ICCP'2022.

Preprint Code Dataset

(2021). ASSANet: An Anisotropic Separable Set Abstraction for Efficient Point Cloud Representation Learning. NeurIPS'21, Spotlight.

Preprint Code

(2021). DeepGCNs: Making GCNs Go as Deep as CNNs. TPAMI'2021.

Preprint Code Project Slides Video

(2021). PU-GCN: Point Cloud Upsampling using Graph Convolutional Networks. CVPR'2021.

Preprint Code Dataset Project Video

(2020). SGAS: Sequential Greedy Architecture Search. CVPR'2020.

Preprint PDF Code Project Slides Video