FASA: Feature Augmentation and Sampling Adaptation for Long-Tailed Instance Segmentation
Y. Zang, C. Huang, C. C. Loy
in Proceedings of IEEE/CVF International Conference on Computer Vision, 2021 (ICCV)
[PDF] [arXiv] [Supplementary Material] [Project Page]

We propose a simple yet effective method, Feature Augmentation and Sampling Adaptation (FASA), that addresses the data scarcity issue by augmenting the feature space especially for rare classes. FASA is a fast, generic method that can be easily plugged into standard or long-tailed segmentation frameworks, with consistent performance gains and little added cost.

ReconfigISP: Reconfigurable Camera Image Processing Pipeline
K. Yu, Z. Li, Y. Peng, C. C. Loy, J. Gu
in Proceedings of IEEE/CVF International Conference on Computer Vision, 2021 (ICCV)
[PDF] [arXiv] [Supplementary Material] [Project Page]

We propose a novel Reconfigurable ISP (ReconfigISP) whose architecture and parameters can be automatically tailored to specific data and tasks. In particular, we implement several ISP modules, and enable back-propagation for each module by training a differentiable proxy, hence allowing us to leverage the popular differentiable neural architecture search and effectively search for the optimal ISP architecture. A proxy tuning mechanism is adopted to maintain the accuracy of proxy networks in all cases.

Focal Frequency Loss for Image Reconstruction and Synthesis
L. Jiang, B. Dai, W. Wu, C. C. Loy
in Proceedings of IEEE/CVF International Conference on Computer Vision, 2021 (ICCV)
[PDF] [arXiv] [Supplementary Material] [Project Page]

We show that narrowing gaps in the frequency domain can ameliorate image reconstruction and synthesis quality further. We propose a novel focal frequency loss, which allows a model to adaptively focus on frequency components that are hard to synthesize by down-weighting the easy ones. This objective function is complementary to existing spatial losses, offering great impedance against the loss of important frequency information due to the inherent bias of neural networks.

3D Human Texture Estimation from a Single Image with Transformers
X. Xu, C. C. Loy
in Proceedings of IEEE/CVF International Conference on Computer Vision, 2021 (ICCV, Oral)
[PDF] [arXiv] [Project Page]

Texformer estimates high-quality 3D human texture from a single image. The Transformer-based method allows efficient information interchange between the image space and UV texture space.

Talk-to-Edit: Fine-Grained Facial Editing via Dialog
Y. Jiang, Z. Huang, X. Pan, C. C. Loy, Z. Liu
in Proceedings of IEEE/CVF International Conference on Computer Vision, 2021 (ICCV)
[PDF] [arXiv] [Supplementary Material] [Project Page]

We propose Talk-to-Edit, an interactive facial editing framework that performs fine-grained attribute manipulation through dialog between the user and the system. Unlike previous works that regard the editing as traversing straight lines in the latent space, here the fine-grained editing is formulated as finding a curving trajectory that respects fine-grained attribute landscape on the semantic field. 2) The curvature at each step is location-specific and determined by the input image as well as the users’ language requests.