Publications

(2025). SwiftEdit: Lightning Fast Text-Guided Image Editing via One-Step Diffusion. Computer Vision and Pattern Recognition (CVPR), 2025.

(2025). Any3DIS: Class-Agnostic 3D Instance Segmentation by 2D Mask Tracking. Computer Vision and Pattern Recognition (CVPR), 2025.

(2025). SharpDepth: Sharpening Metric Depth Predictions Using Diffusion Distillation. Computer Vision and Pattern Recognition (CVPR), 2025.

(2024). Semi-supervised 3D Semantic Scene Completion with 2D Vision Foundation Model Guidance. arXiv:2408.11559.

(2024). SwiftTry: Fast and Consistent Video Virtual Try-On with Diffusion Models. Conference on Artificial Intelligence (AAAI), 2025.

(2024). SwiftBrush V2: Make Your One-step Diffusion Model Better Than Its Teacher. European Conference on Computer Vision (ECCV), 2024.

PDF Code Project

(2023). DiverseDream: Diverse Text-to-3D Synthesis with Augmented Text Embedding. arXiv:2312.02192.

PDF Code Project

(2023). Open3DIS: Open-vocabulary 3D Instance Segmentation with 2D Mask Guidance. Computer Vision and Pattern Recognition (CVPR), 2024.

PDF Code Project

(2023). Stable Messenger: Steganography for Message-Concealed Image Generation. arXiv:2312.01284.

(2023). LP-OVOD: Open-Vocabulary Object Detection by Linear Probing. Winter Conference on Applications of Computer Vision (WACV).

(2023). Dataset Diffusion: Diffusion-based Synthetic Dataset Generation for Pixel-Level Semantic Segmentation. Advances in Neural Information Processing Systems (NeurIPS).

PDF Code Project

(2023). GaPro: Box-Supervised 3D Point Cloud Instance Segmentation Using Gaussian Processes as Pseudo Labelers. International Conference on Computer Vision (ICCV), 2023.

(2023). ISBNet: a 3D Point Cloud Instance Segmentation Network with Instance-aware Sampling and Box-aware Dynamic Convolution,. Computer Vision and Pattern Recognition (CVPR), 2023.

(2022). PSENet: Progressive Self-Enhancement Network for Unsupervised Extreme-Light Image Enhancement. Winter Conference on Applications of Computer Vision (WACV).

(2022). Inductive and Transductive Few-Shot Video Classification via Appearance and Temporal Alignments. European Conference on Computer Vision (ECCV).

(2022). Few Shot Counting and Detection. European Conference on Computer Vision (ECCV), 2022.

(2022). Geodesic-Former: a Geodesic-Guided Few-shot 3D Point Cloud Instance Segmenter. European Conference on Computer Vision (ECCV).

(2022). iFS-RCNN: An Incremental Few-shot Instance Segmenter. Computer Vision and Pattern Recognition (CVPR), 2022.

PDF Code Poster

(2021). POODLE: Improving Few-shot Learning via Penalizing Out-of-Distribution Samples. Advances in Neural Information Processing Systems (NeurIPS).

(2021). A Weakly Supervised Amodal Segmenter with Boundary Uncertainty Estimation. International Conference on Computer Vision (ICCV), 2021.

PDF Code Poster

(2021). FAPIS: A Few-shot Anchor-free Part-based Instance Segmenter. Computer Vision and Pattern Recognition (CVPR), 2021.

PDF Code Poster

(2020). A Self-supervised GAN for Unsupervised Few-shot Object Recognition. ICPR 2020.

(2020). Feature Weighting and Boosting for Few-Shot Segmentation. ICCV 2019.

PDF Code Poster