Tootfinder

ActiveMark: on watermarking of visual foundation models via massive activations
Anna Chistyakova, Mikhail Pautov
https://arxiv.org/abs/2510.04966 https://a…

ActiveMark: on watermarking of visual foundation models via massive activations
Being trained on large and vast datasets, visual foundation models (VFMs) can be fine-tuned for diverse downstream tasks, achieving remarkable performance and efficiency in various computer vision applications. The high computation cost of data collection and training motivates the owners of some VFMs to distribute them alongside the license to protect their intellectual property rights. However, a dishonest user of the protected model's copy may illegally redistribute it, for example, to make …

PanoTPS-Net: Panoramic Room Layout Estimation via Thin Plate Spline Transformation
Hatem Ibrahem, Ahmed Salem, Qinmin Vivian Hu, Guanghui Wang
https://arxiv.org/abs/2510.11992 h…

PanoTPS-Net: Panoramic Room Layout Estimation via Thin Plate Spline Transformation
Accurately estimating the 3D layout of rooms is a crucial task in computer vision, with potential applications in robotics, augmented reality, and interior design. This paper proposes a novel model, PanoTPS-Net, to estimate room layout from a single panorama image. Leveraging a Convolutional Neural Network (CNN) and incorporating a Thin Plate Spline (TPS) spatial transformation, the architecture of PanoTPS-Net is divided into two stages: First, a convolutional neural network extracts the high-l…

Wrist2Finger: Sensing Fingertip Force for Force-Aware Hand Interaction with a Ring-Watch Wearable
Yingjing Xiao (East China Normal University, Shanghai, China), Zhichao Huang (East China Normal University, Shanghai, China), Junbin Ren (East China Normal University, Shanghai, China), Haichuan Song (East China Normal University, Shanghai, China), Yang Gao (East China Normal University, Shanghai, China), Yuting Bai (South China University of Technology, Guangzhou, China), Zhanpeng Jin (So…

Wrist2Finger: Sensing Fingertip Force for Force-Aware Hand Interaction with a Ring-Watch Wearable
Hand pose tracking is essential for advancing applications in human-computer interaction. Current approaches, such as vision-based systems and wearable devices, face limitations in portability, usability, and practicality. We present a novel wearable system that reconstructs 3D hand pose and estimates per-finger forces using a minimal ring-watch sensor setup. A ring worn on the finger integrates an inertial measurement unit (IMU) to capture finger motion, while a smartwatch-based single-channel…

Learning-Based Hashing for ANN Search: Foundations and Early Advances
Sean Moran
https://arxiv.org/abs/2510.04127 https://arxiv.org/pdf/2510.04127

Learning-Based Hashing for ANN Search: Foundations and Early Advances
Approximate Nearest Neighbour (ANN) search is a fundamental problem in information retrieval, underpinning large-scale applications in computer vision, natural language processing, and cross-modal search. Hashing-based methods provide an efficient solution by mapping high-dimensional data into compact binary codes that enable fast similarity computations in Hamming space. Over the past two decades, a substantial body of work has explored learning to hash, where projection and quantisation funct…

One-shot Conditional Sampling: MMD meets Nearest Neighbors
Anirban Chatterjee, Sayantan Choudhury, Rohan Hore
https://arxiv.org/abs/2509.25507 https://arxi…

One-shot Conditional Sampling: MMD meets Nearest Neighbors
How can we generate samples from a conditional distribution that we never fully observe? This question arises across a broad range of applications in both modern machine learning and classical statistics, including image post-processing in computer vision, approximate posterior sampling in simulation-based inference, and conditional distribution modeling in complex data settings. In such settings, compared with unconditional sampling, additional feature information can be leveraged to enable mo…

Highly robust factored principal component analysis for matrix-valued outlier accommodation and explainable detection via matrix minimum covariance determinant
Wenhui Wu, Changchun Shang, Jianhua Zhao, Xuan Ma, Yue Wang
https://arxiv.org/abs/2509.25957

Highly robust factored principal component analysis for matrix-valued outlier accommodation and explainable detection via matrix minimum covariance determinant
Principal component analysis (PCA) is a classical and widely used method for dimensionality reduction, with applications in data compression, computer vision, pattern recognition, and signal processing. However, PCA is designed for vector-valued data and encounters two major challenges when applied to matrix-valued data with heavy-tailed distributions or outliers: (1) vectorization disrupts the intrinsic matrix structure, leading to information loss and the curse of dimensionality, and (2) PCA …

ARTDECO: Towards Efficient and High-Fidelity On-the-Fly 3D Reconstruction with Structured Scene Representation
Guanghao Li, Kerui Ren, Linning Xu, Zhewen Zheng, Changjian Jiang, Xin Gao, Bo Dai, Jian Pu, Mulin Yu, Jiangmiao Pang
https://arxiv.org/abs/2510.08551

ARTDECO: Towards Efficient and High-Fidelity On-the-Fly 3D Reconstruction with Structured Scene Representation
On-the-fly 3D reconstruction from monocular image sequences is a long-standing challenge in computer vision, critical for applications such as real-to-sim, AR/VR, and robotics. Existing methods face a major tradeoff: per-scene optimization yields high fidelity but is computationally expensive, whereas feed-forward foundation models enable real-time inference but struggle with accuracy and robustness. In this work, we propose ARTDECO, a unified framework that combines the efficiency of feed-forw…

OTR: Synthesizing Overlay Text Dataset for Text Removal
Jan Zdenek, Wataru Shimoda, Kota Yamaguchi
https://arxiv.org/abs/2510.02787 https://arxiv.org/pdf/2…

OTR: Synthesizing Overlay Text Dataset for Text Removal
Text removal is a crucial task in computer vision with applications such as privacy preservation, image editing, and media reuse. While existing research has primarily focused on scene text removal in natural images, limitations in current datasets hinder out-of-domain generalization or accurate evaluation. In particular, widely used benchmarks such as SCUT-EnsText suffer from ground truth artifacts due to manual editing, overly simplistic text backgrounds, and evaluation metrics that do not ca…