output
19932026
Showing 2025 · cs.CVShow all

5 papers · 2 filters

cs.CV2025

Vision-Language Memory for Spatial Reasoning

Zuntao Liu, Yi Du, Taimeng Fu +3

Spatial reasoning is a critical capability for intelligent robots, yet current vision-language models (VLMs) still fall short of human-level performance in video-based spatial reas…

cs.CV2025★ 1 cited

Latent Diffusion Unlearning: Protecting Against Unauthorized Personalization Through Trajectory Shifted Perturbations

Naresh Kumar Devulapally, Shruti Agarwal, Tejas Gokhale +1

Text-to-image diffusion models have demonstrated remarkable effectiveness in rapid and high-fidelity personalization, even when provided with only a few user images. However, the e…

cs.CV2025★ 2 cited

Ridgeformer: Mutli-Stage Contrastive Training For Fine-grained Cross-Domain Fingerprint Recognition

Shubham Pandey, Bhavin Jawade, Srirangaraj Setlur

The increasing demand for hygienic and portable biometric systems has underscored the critical need for advancements in contactless fingerprint recognition. Despite its potential,…

cs.CV2025★ 8 cited

SuperPC: A Single Diffusion Model for Point Cloud Completion, Upsampling, Denoising, and Colorization

Yi Du, Zhipeng Zhao, Shaoshu Su +4

Point cloud (PC) processing tasks-such as completion, upsampling, denoising, and colorization-are crucial in applications like autonomous driving and 3D reconstruction. Despite sub…

cs.CV2025

Aligning Instance-Semantic Sparse Representation towards Unsupervised Object Segmentation and Shape Abstraction with Repeatable Primitives

Jiaxin Li, Hongxing Wang, Jiawei Tan +2

Understanding 3D object shapes necessitates shape representation by object parts abstracted from results of instance and semantic segmentation. Promising shape representations enab…