activity
20222024
most citedLess is More: Consistent Video Depth Estimation with Masked Frames Modeling

22 citations · 28 across the 11 of their papers we have counts for

collaborators

11 papers

cs.CV20243 cited

Exposure Completing for Temporally Consistent Neural High Dynamic Range Video Rendering

Jiahao Cui, Wei Jiang, Zhan Peng +2

High dynamic range (HDR) video rendering from low dynamic range (LDR) videos where frames are of alternate exposure encounters significant challenges, due to the exposure change an…

cs.CV2024

Camera-LiDAR Cross-modality Gait Recognition

Wenxuan Guo, Yingping Liang, Zhiyu Pan +3

Gait recognition is a crucial biometric identification technique. Camera-based gait recognition has been widely applied in both research and industrial fields. LiDAR-based gait rec…

cs.CV2024

Pseudo-Labeling by Multi-Policy Viewfinder Network for Image Cropping

Zhiyu Pan, Kewei Wang, Yizheng Wu +4

Automatic image cropping models predict reframing boxes to enhance image aesthetics. Yet, the scarcity of labeled data hinders the progress of this task. To overcome this limitatio…

cs.CV2024

Instance Consistency Regularization for Semi-Supervised 3D Instance Segmentation

Yizheng Wu, Zhiyu Pan, Kewei Wang +5

Large-scale datasets with point-wise semantic and instance labels are crucial to 3D instance segmentation but also expensive. To leverage unlabeled data, previous semi-supervised 3…

cs.CV2024

Geometry-aware Reconstruction and Fusion-refined Rendering for Generalizable Neural Radiance Fields

Tianqi Liu, Xinyi Ye, Min Shi +4

Generalizable NeRF aims to synthesize novel views for unseen scenes. Common practices involve constructing variance-based cost volumes for geometry reconstruction and encoding 3D d…

cs.NE2024

Converting High-Performance and Low-Latency SNNs through Explicit Modelling of Residual Error in ANNs

Zhipeng Huang, Jianhao Ding, Zhiyu Pan +4

Spiking neural networks (SNNs) have garnered interest due to their energy efficiency and superior effectiveness on neuromorphic chips compared with traditional artificial neural ne…