5561 papers
This paper proposes UD-SfPNet, a unified deep learning framework that jointly performs underwater image descattering and shape-from-polarization 3D reconstruction to significantly improve surface normal estimation accuracy in scattering environments.
This paper presents a hierarchical deterministic algorithm that extracts exact axis-aligned rectangular tessellations from finite planar grids by combining composite discovery, minimal representative form normalization, and prime extraction to address the limitations of existing symbolic pattern recognition methods.
VGGT-Det is a novel framework for sensor-geometry-free multi-view indoor 3D object detection that integrates a Visual Geometry Grounded Transformer (VGGT) encoder with attention-guided query generation and query-driven feature aggregation to effectively leverage internal semantic and geometric priors, achieving state-of-the-art performance on ScanNet and ARKitScenes without requiring calibrated camera poses.
This paper introduces DriveCode, a novel numerical encoding method that represents numbers as dedicated embeddings instead of discrete tokens to overcome precision and efficiency limitations, thereby significantly improving trajectory prediction and control signal generation in LLM-based autonomous driving systems.
This paper demonstrates that current vision-language models significantly underperform when analyzing handwritten student work, particularly in identifying and diagnosing errors made by struggling learners, highlighting a critical gap between their problem-solving capabilities and the specific needs of educational applications.
This paper addresses the limitations of existing Standard Dynamic Range (SDR) models in assessing High Dynamic Range (HDR) user-generated content by introducing "Beyond8Bits," a large-scale subjective dataset, and "HDR-Q," a state-of-the-art Multimodal Large Language Model equipped with an HDR-aware vision encoder and a novel reinforcement learning framework to achieve superior quality assessment.
The paper proposes StegoNGP, a parameter-free 3D cryptographic steganography method that leverages Instant-NGP's hash encoding as a key-controlled mechanism to securely embed a complete hidden 3D scene within a single neural network model indistinguishable from a standard cover scene, while offering high capacity, imperceptibility, and robustness through an enhanced multi-key scheme.
This paper demonstrates that the saturating similarity clamping used in Contrastive Forward-Forward learning significantly increases training variance on datasets like CIFAR-10 due to gradient truncation at early layers, a dataset-dependent effect that can be eliminated by switching to a gradient-neutral margin subtraction formulation without compromising mean accuracy.
This paper introduces VeGaS, a novel 4D Gaussian Splatting framework that decouples motion and geometry by employing a Galilean shearing matrix for time-varying velocity and a Geometric Deformation Network to achieve state-of-the-art high-fidelity dynamic scene reconstruction.
EraseAnything++ is a unified framework that enables effective concept erasure in rectified flow-based image and video diffusion models by formulating the task as a constrained multi-objective optimization problem and employing implicit gradient surgery, LoRA-based tuning, and an anchor-and-propagate mechanism to balance removal efficacy with generative quality and temporal consistency.
This paper proposes an Anatomy-Informed Synthetic Supervised Pre-training framework that bridges the semantic gap in formula-driven learning by replacing generic primitives with de-identified anatomical masks and a structure-aware placement strategy, thereby achieving superior performance and scalability in 3D medical segmentation while ensuring privacy compliance.
This paper proposes Event-Anchored Frame Selection (EFS), a training-free, hierarchical framework that partitions videos into semantic events and selects query-relevant anchor frames to optimize keyframe diversity and coverage, significantly enhancing the long-video understanding capabilities of large vision-language models.
This paper addresses the limitations of existing formula-driven synthetic data by proposing a Physics-inspired Spatially-Decoupled Synthesis framework that resolves the texture-shape conflict through a gradient-shielded buffer zone and spectral texture injection, thereby significantly enhancing the performance of 3D medical Vision Transformers on BTCV and MSD datasets without relying on real patient data.
This paper presents a comprehensive technical survey on foundation models in remote sensing, exploring their evolution from unimodal to multimodal approaches while providing a tutorial-like guide to help researchers understand, train, and apply these models to real-world tasks.
MLRecon is a robust, low-cost framework for markerless freehand 3D ultrasound reconstruction that utilizes a commodity RGB-D camera and a vision foundation model-based pipeline with a dual-stage refinement network to achieve drift-resilient, sub-millimeter accurate probe pose tracking and high-quality volumetric imaging.
The paper proposes GeodesicNVS, a novel view synthesis framework that combines deterministic Data-to-Data Flow Matching with Probability Density Geodesic constraints derived from pretrained diffusion models to achieve superior view consistency and geometric coherence compared to traditional diffusion-based approaches.
This paper discusses the implementation of car license plate recognition systems, highlighting their growing necessity in Malaysia due to increasing vehicle numbers and their diverse applications in traffic management, law enforcement, and other specialized fields.
This paper proposes RaUF, a spatial uncertainty field learning framework that addresses the low fidelity and ambiguity of millimeter-wave radar by modeling anisotropic probabilistic uncertainty and employing a bidirectional domain attention mechanism to suppress spurious returns, thereby delivering highly reliable spatial detections with well-calibrated uncertainty for downstream perception tasks.
This paper proposes Content-Aware Frequency Encoding (CAFE) and its enhanced variant CAFE+, which utilize learnable parallel linear layers and Chebyshev features to overcome the spectral bias of Implicit Neural Representations by explicitly synthesizing and selecting task-relevant frequency bases for superior signal reconstruction.
The paper proposes VL-Anomaly, a novel framework that leverages vision-language model priors and a multi-source inference strategy to significantly improve road anomaly segmentation by reducing false positives on normal backgrounds and enhancing the detection of out-of-distribution obstacles.