11 papers
TV-AudioRemover: Joint Text-Visual Guided Sound Removal with Multi-Task Hard-Mixture Curriculum
Xinyue Guo, Jianxuan Yang, Daiguo Zhou +4
Visual object removal can eliminate a target from video frames, yet its acoustic trace persists in the soundtrack, causing obvious audio-visual inconsistency. Existing video inpain…
LoViF 2026 The First Challenge on Unified Removal of Raindrops and Reflections: Methods and Results
Zewei He, Xi Tong, Yu Chen +49
This workshop paper comprehensively reviews the First Challenge on Unified Removal of Raindrops and Reflections. The challenge aims to address a frequently encountered practical pr…
GRNEdit: Efficient General Video Editing from a New Binary-Evidence Perspective in Generative Refinement Networks
Feng Xie, Jiagao Hu, Fuhao Li +5
Instruction-based general video editing seeks to unify diverse editing operations within a single, intuitive interface. Existing approaches often rely on resource-intensive conditi…
From Synthesis to Removal: Physics-Grounded Reflection Simulation and Diffusion-Based Video Dereflection
Zepeng Wang, Jiagao Hu, Fuhao Li +3
Videos captured through glass often contain reflections that degrade visual quality and interfere with downstream vision tasks. Although single-image reflection removal has been ex…
Beyond Information Redundancy: Expanding Cross-Modal Knowledge Representation for Power Load Time Series Forecasting
Yuxuan Chen, Shuo Dai, Ruoyi Xu +1
Load forecasting is pivotal for stable power systems. Conventional uni-modal methods suffer from representation drift under data scarcity. While recent multi-modal approaches attem…
PROVE: A Perceptual RemOVal cohErence Benchmark for Visual Media
Fuhao Li, Shaofeng You, Jiagao Hu +6
Evaluating object removal in images and videos remains challenging because the task is inherently one-to-many, yet existing metrics frequently disagree with human perception. Full-…
Dynamic Execution Commitment of Vision-Language-Action Models
Feng Chen, Xianghui Wang, Yuxuan Chen +4
Vision-Language-Action (VLA) models predominantly adopt action chunking, i.e., predicting and committing to a short horizon of consecutive low-level actions in a single forward pas…
From Ideal to Real: Stable Video Object Removal under Imperfect Conditions
Jiagao Hu, Yuxuan Chen, Fuhao Li +4
Removing objects from videos remains difficult in the presence of real-world imperfections such as shadows, abrupt motion, and defective masks. Existing diffusion-based video inpai…
What to Learn: Features, Image Transformations, or Both?
Yuxuan Chen, Binbin Xu, Frederike Dümbgen +1
Long-term visual localization is an essential problem in robotics and computer vision, but remains challenging due to the environmental appearance changes caused by lighting and se…
Self-Supervised Feature Learning for Long-Term Metric Visual Localization
Yuxuan Chen, Timothy D. Barfoot
Visual localization is the task of estimating camera pose in a known scene, which is an essential problem in robotics and computer vision. However, long-term visual localization is…
SLIC: Self-Supervised Learning with Iterative Clustering for Human Action Videos
Salar Hosseini Khorasgani, Yuxuan Chen, Florian Shkurti
Self-supervised methods have significantly closed the gap with end-to-end supervised learning for image classification. In the case of human action videos, however, where both appe…