8694 papers
The paper proposes UHDPromer, a neural discrimination-prompted Transformer that leverages Neural Discrimination Priors to measure feature differences and guide attention and gating mechanisms, achieving state-of-the-art efficiency and performance across three Ultra-High-Definition image restoration tasks.
PPC-MT is a novel parallel point cloud completion framework that combines a PCA-guided parallel synthesis strategy with a hybrid Mamba-Transformer architecture to achieve superior reconstruction quality and computational efficiency compared to state-of-the-art methods.
This paper introduces Multi-Membership Temporal Attention (MMTA), a unified single-stage transformer architecture that enhances fine-grained stroke rehabilitation assessment by enabling frames to attend to multiple temporal contexts simultaneously, thereby improving boundary sensitivity and performance on both video and IMU data without increasing model depth.
This paper proposes SMART, a novel semi-supervised framework leveraging a SAM3-based teacher-student architecture with motion-aware consistency and progressive confidence regularization to achieve state-of-the-art coronary artery segmentation in X-ray angiography videos while significantly reducing the need for annotated data.
This paper presents a novel blind nonlinear inverse framework that unifies anatomical image recovery, high-resolution cine synthesis, and 3D motion estimation for tagged MRI by synergistically combining MR physics with deep generative priors to overcome challenges like tag fading and imaging blur.
VEMamba is an efficient framework for isotropic reconstruction of Volume Electron Microscopy that leverages a novel 3D dependency reordering paradigm with Axial-Lateral Chunking Selective Scan and Dynamic Weights Aggregation modules, alongside MoCo-based degradation-aware training, to achieve high-performance, consistent 3D tissue imaging with a low computational footprint.
The paper introduces pySpatial, a zero-shot visual programming framework that enhances Multi-modal Large Language Models' spatial reasoning capabilities by generating Python code to interface with 3D spatial tools, thereby outperforming existing baselines on benchmarks and enabling successful real-world indoor navigation without fine-tuning.
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.