3835 papers
This paper introduces the Graded Fast Hard Thresholding Pursuit (GFHTP) algorithm, which utilizes a quantile-truncated step size for LAD minimization to achieve exact sparse signal recovery from outlier-contaminated measurements without requiring prior knowledge of the signal's sparsity level.
SpatialMem is a memory-centric system that constructs a metric-aligned 3D scaffold from casual egocentric RGB videos to enable efficient, interpretable long-horizon language grounding, retrieval, and QA by linking open-vocabulary object nodes to spatial coordinates without requiring specialized sensors.
The paper introduces OnlineSI, a framework that enables Multimodal Large Language Models to continuously improve spatial understanding and grounding in dynamic environments by maintaining a finite spatial memory and integrating 3D point cloud data with semantic information.
This paper introduces SRA 2, a lightweight intrinsic guidance framework that accelerates diffusion transformer training and improves generation quality by aligning intermediate latent features with pre-trained VAE features via a simple projection layer, eliminating the need for external encoders or dual-model setups while incurring minimal computational overhead.
The paper introduces FARTrack, a fast autoregressive visual tracking framework that leverages Task-Specific Self-Distillation and Inter-frame Autoregressive Sparsification to achieve real-time, high-performance tracking (70.6% AO on GOT-10k) with exceptional inference speeds of up to 343 FPS on GPU and 121 FPS on CPU.
The paper introduces SpatialReward, a reward model that leverages explicit spatial reasoning to overcome the "Attention Collapse" limitation in existing evaluators, thereby providing fine-grained, accurate signals that significantly enhance online reinforcement learning performance for image editing tasks.
The paper proposes (MGS)-Net, a geometry-grounded framework that unifies Micro-Geometric Scale Adaptation and Macro-Geometric Structure Filtering to overcome geometric misalignment and achieve state-of-the-art cross-view geo-localization performance.
This paper introduces MiDAS, an open-source, platform-agnostic system that enables non-invasive, time-synchronized multimodal data acquisition for robot-assisted minimally invasive surgery, validated by demonstrating that its external sensing approach achieves gesture recognition performance comparable to proprietary telemetry while releasing the first annotated dataset for hernia repair suturing.
DAV-GSWT is a data-efficient framework that combines diffusion priors with active view sampling to synthesize high-fidelity Gaussian Splatting Wang Tiles from minimal input observations, enabling the generation of expansive, photorealistic landscapes without relying on densely sampled exemplar reconstructions.
The paper proposes RobSelf, a robust self-supervised model that jointly optimizes a misalignment-aware feature translator and a content-aware reference filter to achieve state-of-the-art cross-modal super-resolution on real-world misaligned data with significantly improved efficiency.
UrbanAlign proposes a novel post-hoc calibration framework that aligns frozen vision-language models with human preferences for urban scene assessment by mining interpretable dimensions, extracting robust concept scores via an Observer-Debater-Judge chain, and calibrating them through locally-weighted ridge regression, achieving state-of-the-art accuracy without any model retraining.
This paper demonstrates that affordance reasoning in Vision Foundation Models can be achieved in a zero-shot, training-free manner by fusing DINO's inherent geometric part structures with Flux's verb-conditioned interaction priors, thereby establishing geometric and interaction perception as the fundamental, composable building blocks of affordance understanding.
StoryTailor is a zero-shot pipeline that generates temporally coherent, action-rich multi-subject visual narratives on a single RTX 4090 by synergizing Gaussian-Centered Attention, Action-Boost Singular Value Reweighting, and a Selective Forgetting Cache to simultaneously ensure action faithfulness, subject identity fidelity, and cross-frame background continuity.
The paper introduces UniVBench, a comprehensive benchmark featuring 200 high-quality, human-created multi-shot videos and a unified agentic evaluation system (UniV-Eval) to holistically assess video foundation models across understanding, generation, editing, and reconstruction tasks, addressing the limitations of existing fragmented and task-specific evaluations.
This paper introduces a geometry-aware Graph Neural Network autodecoder that leverages protein-structure priors and ellipsoidal support lifting to achieve higher accuracy in heterogeneous single-particle cryo-EM reconstruction compared to traditional MLP-based methods.
The paper introduces DPCache, a training-free acceleration framework for diffusion models that formulates sampling as a global path planning problem and utilizes dynamic programming on a path-aware cost tensor to select optimal key timesteps, thereby achieving significant speedups with minimal quality loss and even surpassing full-step baselines in certain metrics.
This paper introduces Synthetic Visual Genome 2 (SVG2), a large-scale automated panoptic video scene graph dataset with over 636K videos, and presents TRaSER, a novel model that leverages trajectory-aligned token mechanisms to significantly outperform existing baselines in scene graph generation and downstream video question answering tasks.
This paper proposes a novel adaptive dynamic dehazing framework that utilizes a closed-loop optimization mechanism combining task performance feedback and text-based instruction guidance to enable real-time, training-free adaptation of dehazing outputs for diverse downstream vision tasks.
This paper introduces PanScale, a large-scale cross-scale pansharpening dataset and benchmark, alongside ScaleFormer, a novel transformer-based architecture that achieves superior generalization across varying image resolutions by reframing scale adaptation as sequence length generalization through tokenization and rotary positional encoding.
Mobile-VTON is a high-fidelity, privacy-preserving framework that enables fully offline virtual try-on on commodity mobile devices by utilizing a modular TGT architecture with feature-guided adversarial distillation and trajectory-consistency training to match server-based performance without requiring cloud computing.