activity
20212026
most citedPlane2Depth: Hierarchical Adaptive Plane Guidance for Monocular Depth Estimation

6 citations · 20 across the 21 of their papers we have counts for

collaborators
Showing cs.CVShow all

26 papers · 1 filter

cs.CV2026

PriorPose: Reference-Guided Joint Deformation and Alignment for Category-Level Object Pose Estimation

Yihan Chen, Huan Ren, Wenfei Yang +3

Category-level object pose estimation seeks to recover a similarity transform for unseen instances without instance-specific CAD models. Most competitive methods are corr…

cs.CV2026

TopoSurfel: Closing the Loop between Gaussian Surfels and Meshes for Surface Reconstruction

Chuanjin Fan, Wenjie Chang, Bohao Liao +3

3D Gaussian Splatting has achieved remarkable success in novel view synthesis. However, extracting high-fidelity surfaces directly from 3DGS remains challenging due to its discrete…

cs.CV2026

Adversarial Attacks Already Tell the Answer: Directional Bias-Guided Test-time Defense for Vision-Language Models

Liangsheng Liu, Si Chen, Jiamin Wu +5

Vision-Language Models (VLMs), such as CLIP, have shown strong zero-shot generalization but remain highly vulnerable to adversarial perturbations, posing serious risks in real-worl…

cs.CV2026

ExMesh: Explicit Mesh Reconstruction with Topology Adaptation

Chuanjin Fan, Lifan Wu, Wenjie Chang +3

Reconstructing surface meshes from multi-view images has remained a core challenge in recent years. Most existing methods, whether implicit or explicit, depend on intermediate repr…

cs.CV2026

ComPose: A Unified Completion-Pose Framework for Robust Category-Level Object Pose Estimation

Huan Ren, Yihan Chen, Chuxin Wang +3

Category-level object pose estimation aims to predict the pose and size of arbitrary objects in specific categories. Existing methods struggle with the inherent incompleteness of o…

cs.CV2026

GeoGuide: Hierarchical Geometric Guidance for Open-Vocabulary 3D Semantic Segmentation

Xujing Tao, Chuxin Wang, Yubo Ai +8

Open-vocabulary 3D semantic segmentation aims to segment arbitrary categories beyond the training set. Existing methods predominantly rely on distilling knowledge from 2D open-voca…