Detection, segmentation, depth and recognition research, plus the vision backbones that keep displacing the last generation.
arXiv:2603.12064v3 Announce Type: replace Abstract: We address the challenging problem of dense dynamic scene reconstruction and camera pose estimation from multiple freely moving cameras -- a settin...
The HSI‑Road dataset now includes manually labeled six‑class road‑scene annotations (Background, Asphalt, Concrete, Dirt, Water, Grass) and a pipeline for RGB‑to‑NIR registration. Six semantic‑segmentation models were evaluated on four input types—original‑resolution RGB, registered low‑resolution RGB, NIR, and stacked RGB‑NIR—using per‑class and mean IoU and F1 scores. Results show that high‑resolution RGB yields the best overall performance, but at matched resolution the stacked RGB‑NIR input consistently outperforms NIR alone and often surpasses registered RGB, especially for the Water class.
RA‑SOD is a new RGB‑Thermal salient object detection framework that explicitly models the reliability of each modality. It introduces a reliability‑conditioned representation, an uncertainty‑guided dual‑stream refinement, and a pixel‑wise modality competition mechanism to adaptively compensate degraded features and suppress unreliable evidence. Experiments on four benchmarks show that RA‑SOD achieves state‑of‑the‑art performance and remains robust under severe modality degradation.
arXiv:2609.13043v1 Announce Type: new Abstract: Robust medical image segmentation across imaging modalities is challenging because of large differences in appearance and intensity distributions. Mode...
Uni-HOI is a unified framework that learns the joint distribution among text, human motion, and object motion for 4D human‑object interaction (HOI). It uses large language models and two motion‑specific VQ‑VAEs to convert heterogeneous motion data into token sequences, enabling seamless integration of all three modalities. A two‑stage training strategy first captures correlations on a large‑scale HOI dataset and then fine‑tunes for specific tasks, achieving strong performance on text‑driven HOI generation, object‑motion‑driven human motion generation, and human‑motion‑driven object motion prediction.
arXiv:2609.12825v1 Announce Type: new Abstract: State Space Models (SSMs), particularly VMamba, have emerged as efficient alternatives for modeling long-range dependencies in medical image analysis....
arXiv:2609.12798v1 Announce Type: new Abstract: Camouflaged object detection (COD) is an important engineering task in intelligent optical perception, but it remains challenging when targets closely...
arXiv:2609.12155v1 Announce Type: new Abstract: Understanding person-level bi-manual interactions requires not only detecting hands, but also identifying which two hands belong to the same person and...
arXiv:2609.12350v1 Announce Type: new Abstract: Close-range first-person field images are important for mobile maize phenotyping because many plant-level traits depend on in-canopy structures that ar...
arXiv:2609.12898v1 Announce Type: new Abstract: Fine-grained robotic manipulation depends on understanding parts, not only whole objects. Existing 3D foundation models tend to be either generalized b...
RoES is a Rotational Equivariant Selective-frequency fusion network that dynamically separates low- and high-frequency components of infrared-visible images. It uses a trainable rotation-enhanced updater to decouple frequencies, then fuses them with a dual-branch module: a rotation-equivariant Mamba for low-frequency structural dependencies and a polar spectral attention Dual-Fourier block for high-frequency detail refinement. Experiments show RoES outperforms existing methods in fusion quality and downstream object detection, offering a robust multimodal fusion solution.
The paper introduces CELM, a data‑free framework for federated learning that estimates class‑wise contribution by maximizing logits. It constructs a cross‑client evidence matrix to quantify each client’s competence and coverage for each class, then uses this matrix to compute weighted aggregation that upweights clients offering strong evidence for underrepresented classes. The method maintains stability through simplex constraints and momentum smoothing, and it is compatible with standard FL pipelines, showing improved robustness to class imbalance and heterogeneity on vision benchmarks.
arXiv:2609.12920v1 Announce Type: new Abstract: We model total latency as the convolution of preprocessing, inference, and postprocessing distributions under a simplifying independence approximation,...
The paper introduces GNM Head, a generative anthropometric model that extends beyond traditional head models by including detailed ocular and intra‑oral structures such as eyeballs, teeth, and tongue. Built from a large collection of high‑resolution 3D scans and artist‑crafted samples, GNM offers improved geometric fidelity and state‑of‑the‑art fitting performance for target 3D face scans. The authors release the full framework publicly to support further research and development.
The paper introduces an open, modular AI framework that automatically detects and structures evidence of social tipping points in climate literature at the passage level. It integrates a DistilBERT boundary splitter, an iteratively augmented RoBERTa classifier, a Mistral 7B rewrite model, a LLaMA 3.2 3B rating model, and a Milvus vector store, all accessible via a Streamlit interface. Evaluation on a GPT‑4.1‑labelled benchmark and expert‑reviewed set shows the splitter outperforms competitors and the RoBERTa detector achieves high accuracy and agreement.
The paper introduces GMPCR, a non‑learning spectral consistency‑guided framework for multiview point cloud registration in low‑overlap scenes. GMPCR refines initial correspondences into a second‑order compatibility structure, uses spectral analysis to filter unreliable matches and select informative scan pairs, and then applies maximal‑clique hypothesis generation for robust relative transformations. The resulting sparse pose graph is further refined with an adaptive history‑aware synchronization scheme, and a recovery mechanism allows previously down‑weighted edges to regain confidence, achieving high registration recalls on benchmark datasets while reducing computational cost.
EgoFun3D introduces a coordinated task, dataset, and benchmark for creating simulation-ready interactive 3D objects from egocentric videos. The approach captures general cross-part functional mappings via function templates, enabling precise evaluation and direct compilation into executable code. A 4‑stage pipeline—2D part segmentation, reconstruction, articulation estimation, and function template inference—is proposed, and a dataset of 517 videos with detailed annotations is released for comprehensive benchmarking.
BodhiPromptShield is a policy‑aware mediation layer for LLM agent pipelines that detects sensitive text spans before they propagate, replacing them with typed placeholders, semantic abstractions, or secure tokens and restoring them only at authorized execution boundaries. In evaluations on AI4Privacy, PrivacyLens, and AgentDojo datasets, the system reduces identifier exposure to 7.4% and 1.8% respectively, and limits exact identifier leakage in final actions to 2.1–3.1%. While mediation preserves factual content according to automated metrics, human annotations show a significant drop in inferability from 100% to 24–53%, indicating the need for human validation of semantic‑leakage measures.
arXiv:2606.10468v2 Announce Type: replace Abstract: Coastline detection in remotely sensed imagery is commonly formulated as pixel-wise segmentation, even though coastlines used in coastal monitoring...
The paper introduces a physics-guided synthetic high‑frequency ultrasound (HFUS) generation framework for skin layer segmentation. It builds multilayer acoustic skin phantoms, assigns layer‑dependent acoustic properties, and uses k‑Wave simulation to produce paired synthetic HFUS images, dense layer masks, and metadata. When used to pretrain segmentation models and fine‑tuned on real HFUS data, the synthetic pretraining yields performance comparable to real‑only training and improves mean Dice/IoU in most architectures, indicating that the synthetic images carry transferable anatomical and textural cues.