activity
20242026
collaborators

10 papers

cs.CV2026

UniE2F: A Unified Diffusion Framework for Event-to-Frame Reconstruction with Video Foundation Models

Gang Xu, Zhiyu Zhu, Junhui Hou

Event cameras excel at high-speed, low-power, and high-dynamic-range scene perception. However, as they fundamentally record only relative intensity changes rather than absolute in…

cs.CV2026

Is Contrastive Distillation Enough for Learning Comprehensive 3D Representations?

Yifan Zhang, Junhui Hou

Cross-modal contrastive distillation has recently been explored for learning effective 3D representations. However, existing methods focus primarily on modality-shared features, ne…

cs.CV2026

Unsupervised Online 3D Instance Segmentation with Synthetic Sequences and Dynamic Loss

Yifan Zhang, Wei Zhang, Chuangxin He +2

Unsupervised online 3D instance segmentation is a fundamental yet challenging task, as it requires maintaining consistent object identities across LiDAR scans without relying on an…

cs.CV2026

Optimizing Multi-Modality Trackers via Significance-Regularized Tuning

Zhiwen Chen, Jinjian Wu, Zhiyu Zhu +3

This paper tackles the critical challenge of optimizing multi-modality trackers by effectively adapting pre-trained models for RGB data. Existing fine-tuning paradigms oscillate be…

cs.CV2026

Joint Orientation and Weight Optimization for Robust Watertight Surface Reconstruction via Dirichlet-Regularized Winding Fields

Jiaze Li, Daisheng Jin, Fei Hou +5

We propose Dirichlet Winding Reconstruction (DiWR), a robust method for reconstructing watertight surfaces from unoriented point clouds with non-uniform sampling, noise, and outlie…

cs.CV2025

RoSe: Robust Self-supervised Stereo Matching under Adverse Weather Conditions

Yun Wang, Junjie Hu, Junhui Hou +3

Recent self-supervised stereo matching methods have made significant progress, but their performance significantly degrades under adverse weather conditions such as night, rain, an…