Publications (22)
VIEW2SPACE: Studying Multi-View Visual Reasoning from Sparse Observations
Fucai Ke, Zhixi Cai, Boying Li +6
Multi-view visual reasoning is essential for intelligent systems that must understand complex environments from sparse and discrete viewpoints, yet existing research has largely fo…
3DOT: Texture Transfer for 3DGS Objects from a Single Reference Image
Xiao Cao, Beibei Lin, Bo Wang +2
3D texture swapping allows for the customization of 3D object textures, enabling efficient and versatile visual transformations in 3D editing. While no dedicated method exists, ada…
NightHaze: Nighttime Image Dehazing via Self-Prior Learning
Beibei Lin, Yeying Jin, Wending Yan +3
Masked autoencoder (MAE) shows that severe augmentation during training produces robust representations for high-level tasks. This paper brings the MAE-like framework to nighttime…
GaitStrip: Gait Recognition via Effective Strip-based Feature Representations and Multi-Level Framework
Ming Wang, Beibei Lin, Xianda Guo +5
Many gait recognition methods first partition the human gait into N-parts and then combine them to establish part-based feature representations. Their gait recognition performance…
Enhancing Visibility in Nighttime Haze Images Using Guided APSF and Gradient Adaptive Convolution
Yeying Jin, Beibei Lin, Wending Yan +3
Visibility in hazy nighttime scenes is frequently reduced by multiple factors, including low light, intense glow, light scattering, and the presence of multicolored light sources.…
GaitGL: Learning Discriminative Global-Local Feature Representations for Gait Recognition
Beibei Lin, Shunli Zhang, Ming Wang +2
Existing gait recognition methods either directly establish Global Feature Representation (GFR) from original gait sequences or generate Local Feature Representation (LFR) from sev…
Gait Recognition via Effective Global-Local Feature Representation and Local Temporal Aggregation
Beibei Lin, Shunli Zhang, Xin Yu
Gait recognition is one of the most important biometric technologies and has been applied in many fields. Recent gait recognition frameworks represent each gait frame by descriptor…
WeatherReasonSeg: A Benchmark for Weather-Aware Reasoning Segmentation in Visual Language Models
Wanjun Du, Zifeng Yuan, Tingting Chen +3
Existing vision-language models (VLMs) have demonstrated impressive performance in reasoning-based segmentation. However, current benchmarks are primarily constructed from high-qua…
Gait Recognition with Mask-based Regularization
Chuanfu Shen, Beibei Lin, Shunli Zhang +3
Most gait recognition methods exploit spatial-temporal representations from static appearances and dynamic walking patterns. However, we observe that many part-based methods neglec…
HypoSpace: A Diagnostic Benchmark for Set-Valued Hypothesis Generation under Underdetermination and Sublinear Coverage Bounds
Tingting Chen, Beibei Lin, Zifeng Yuan +5
Many scientific problems are underdetermined: multiple distinct hypotheses are equally consistent with the same observations. In such settings, effective inference requires not onl…
NightRain: Nighttime Video Deraining via Adaptive-Rain-Removal and Adaptive-Correction
Beibei Lin, Yeying Jin, Wending Yan +4
Existing deep-learning-based methods for nighttime video deraining rely on synthetic data due to the absence of real-world paired data. However, the intricacies of the real world,…
UENR-600K: A Large-Scale Physically Grounded Dataset for Nighttime Video Deraining
Pei Yang, Hai Ci, Beibei Lin +2
Nighttime video deraining is uniquely challenging because raindrops interact with artificial lighting. Unlike daytime white rain, nighttime rain takes on various colors and appears…
Auto-Discovery-Bench: Diagnosing Structured State Tracking in Oracle-Guided Discovery
Tingting Chen, Beibei Lin, Srinivas Anumasa +5
Interactive discovery requires agents to maintain and update structured beliefs over many rounds of feedback. Before evaluating agents in noisy, open-ended scientific environments,…
Seeing Beyond Haze: Generative Nighttime Image Dehazing
Beibei Lin, Stephen Lin, Robby Tan
Nighttime image dehazing is particularly challenging when dense haze and intense glow severely degrade or entirely obscure background information. Existing methods often struggle d…
GlowGS: Generative Semantic Feature Learning for 3D Gaussian Splatting in Nighttime Glow Scenes
Beibei Lin, Xiao Cao, Jingyuan Guo +1
Existing 3DGS methods effectively render high-quality novel views in clear-day scenes. However, they struggle with night scenes, particularly in glow regions, due to the lack of st…
Gait Recognition in the Wild: A Large-scale Benchmark and NAS-based Baseline
Xianda Guo, Zheng Zhu, Tian Yang +6
Gait benchmarks empower the research community to train and evaluate high-performance gait recognition systems. Even though growing efforts have been devoted to cross-view recognit…
RaindropGS: A Benchmark for 3D Gaussian Splatting under Raindrop Conditions
Zhiqiang Teng, Tingting Chen, Beibei Lin +4
3D Gaussian Splatting (3DGS) under raindrop conditions suffers from severe occlusions and optical distortions caused by raindrop contamination on the camera lens, substantially deg…
GeoComplete: Geometry-Aware Diffusion for Reference-Driven Image Completion
Beibei Lin, Tingting Chen, Robby T. Tan
Reference-driven image completion, which restores missing regions in a target view using additional images, is particularly challenging when the target view differs significantly f…
SSNeRF: Sparse View Semi-supervised Neural Radiance Fields with Augmentation
Xiao Cao, Beibei Lin, Bo Wang +2
Sparse view NeRF is challenging because limited input images lead to an under constrained optimization problem for volume rendering. Existing methods address this issue by relying…
NTIRE 2026 The Second Challenge on Day and Night Raindrop Removal for Dual-Focused Images: Methods and Results
Xin Li, Yeying Jin, Suhang Yao +95
This paper presents an overview of the NTIRE 2026 Second Challenge on Day and Night Raindrop Removal for Dual-Focused Images. Building upon the success of the first edition, this c…
RGB-to-Polarization Estimation: A New Task and Benchmark Study
Beibei Lin, Zifeng Yuan, Tingting Chen
Polarization images provide rich physical information that is fundamentally absent from standard RGB images, benefiting a wide range of computer vision applications such as reflect…
DyGait: Exploiting Dynamic Representations for High-performance Gait Recognition
Ming Wang, Xianda Guo, Beibei Lin +5
Gait recognition is a biometric technology that recognizes the identity of humans through their walking patterns. Compared with other biometric technologies, gait recognition is mo…