23 citations · 67 across the 13 of their papers we have counts for
8 papers · 1 filter
Rendering Humans from Object-Occluded Monocular Videos
Tiange Xiang, Adam Sun, Jiajun Wu +2
3D understanding and rendering of moving humans from monocular videos is a challenging task. Despite recent progress, the task remains difficult in real-world scenarios, where obst…
Seeing Beyond the Brain: Conditional Diffusion Model with Sparse Masked Modeling for Vision Decoding
Zijiao Chen, Jiaxin Qing, Tiange Xiang +2
Decoding visual stimuli from brain recordings aims to deepen our understanding of the human visual system and build a solid foundation for bridging human and computer vision throug…
Towards Bi-directional Skip Connections in Encoder-Decoder Architectures and Beyond
Tiange Xiang, Chaoyi Zhang, Xinyi Wang +4
U-Net, as an encoder-decoder architecture with forward skip connections, has achieved promising results in various medical image analysis tasks. Many recent approaches have also ex…
SQUID: Deep Feature In-Painting for Unsupervised Anomaly Detection
Tiange Xiang, Yixiao Zhang, Yongyi Lu +4
Radiography imaging protocols focus on particular body regions, therefore producing images of great similarity and yielding recurrent anatomical structures across patients. To expl…
DSNet: A Dual-Stream Framework for Weakly-Supervised Gigapixel Pathology Image Analysis
Tiange Xiang, Yang Song, Chaoyi Zhang +6
We present a novel weakly-supervised framework for classifying whole slide images (WSIs). WSIs, due to their gigapixel resolution, are commonly processed by patch-wise classificati…
Walk in the Cloud: Learning Curves for Point Clouds Shape Analysis
Tiange Xiang, Chaoyi Zhang, Yang Song +2
Discrete point cloud objects lack sufficient shape descriptors of 3D geometries. In this paper, we present a novel method for aggregating hypothetical curves in point clouds. Seque…
Two-Stage Monte Carlo Denoising with Adaptive Sampling and Kernel Pool
Tiange Xiang, Hongliang Yuan, Haozhi Huang +1
Monte Carlo path tracer renders noisy image sequences at low sampling counts. Although great progress has been made on denoising such sequences, existing methods still suffer from…
BiO-Net: Learning Recurrent Bi-directional Connections for Encoder-Decoder Architecture
Tiange Xiang, Chaoyi Zhang, Dongnan Liu +3
U-Net has become one of the state-of-the-art deep learning-based approaches for modern computer vision tasks such as semantic segmentation, super resolution, image denoising, and i…