Computer Vision

The paper presents SenseNova-Vision, a unified multimodal model for computer vision tasks using natural language instructions and optional visual prompts, trained primarily on a new corpus and requiri…

This study systematically evaluates Vision Mamba models for detecting AI-generated images, finding that while they show promise, their current strengths and limitations must be understood relative to…

The paper introduces PIXIE, a zero-shot framework for estimating 6D pose of an object from an RGB image using only an untextured 3D model.

This paper identifies and explores a new type of physical adversarial attack on vision systems called Scratch-induced Lens Adversarial Streak Hijacking (SLASH), which causes persistent and selective o…

This paper investigates acoustic attacks on Artificial Intelligence (AI) based computer vision systems using lower frequencies in the audible range, and explores the impact on various image and object…

This paper proposes DPNeXt, a streamlined multi-scale feature fusion decoder for Multi-Task Learning (MTL) in robotics perception systems, improving frozen VFM utilization and mitigating negative indu…

The paper shows that using random cropping, a standard data augmentation technique, can naturally amplify differential privacy guarantees for machine learning models without requiring any changes to t…

Places in the Wild introduces a massive, high-resolution RAW photograph dataset of 67,574 images captured in situ across 810 locations, providing unprecedented detail for ecologically valid vision res…

This study empirically benchmarks classical and quantum machine learning models for image recognition, finding that while quantum models offer superior accuracy and resource efficiency at high dimensi…

The paper introduces ProxyPose, a method for six-degree-of-freedom (6-DoF) pose tracking using a video diffusion model and a single marked pixel in the first frame.

The paper introduces Multi-temporal Referring Segmentation (MTRS), a new task requiring models to segment language-described temporal changes, and proposes MTRefSeg-R1, a specialized framework that ac…

This paper presents an open-source computer vision pipeline for classifying vehicle body types from naturalistic roadway video.

The paper introduces CAIAMAR, a multi-agent reasoning framework that achieves context-aware and high-fidelity anonymization of personally identifiable information (PII) in street imagery, significantl…

The paper introduces PAR3D, a unified part-aware 3D-MLLM framework, to enhance 3D scene understanding by enabling models to reason about and ground both whole objects and their fine-grained parts.

The paper proposes xModel-KD, a cross-modal knowledge distillation framework, to improve 3D point cloud segmentation by effectively transferring rich appearance cues from 2D images to sparse 3D geomet…

The paper reframes industrial visual sim-to-real transfer as a domain-gap problem categorized by the availability of explicit object geometry (CAD), arguing that the required prior evidence dictates t…

The paper proposes a Transformer-based end-to-end architecture to reconstruct 3D house roof wireframes from sparse point clouds and semantic data, achieving state-of-the-art results on the S23DR Chall…

This paper introduces the Complex Social Behavior (CSB) dataset and evaluates the progress of scene description accuracy in vision language models (VLMs) from 2017 to 2025. The authors find that MLLMs…

GeoSAM-3D proposes a novel framework for open-vocabulary 3D scene segmentation from simple monocular video by propagating object prompts using a geodesic distance kernel on a reconstructed Gaussian sc…

This paper introduces CFMME, a comprehensive Chinese financial multimodal benchmark, and evaluates current Large Vision-Language Models (LVLMs), finding that while state-of-the-art models perform mode…