Detection, segmentation, depth and recognition research, plus the vision backbones that keep displacing the last generation.
arXiv:2609.00814v1 Announce Type: new Abstract: Remote sensing visual models have continuously advanced various interpretation tasks. However, the research process behind model improvement still heav...
arXiv:2609.01575v1 Announce Type: new Abstract: Extracting structured fields from hundreds of millions of documents annually remains costly in regulated industries: bespoke OCR cascades cover only a...
arXiv:2604.16729v2 Announce Type: replace-cross Abstract: State-of-the-art large language models (LLMs) show high performance in general visual question answering. However, a fundamental limitation r...
Pix2Rep-v2 is a self‑supervised learning framework that learns pixel‑ and voxel‑level representations for dense medical imaging tasks, using a redundancy‑reduction objective and equivariance principles to scale to 3D and wide field‑of‑view data. The method is evaluated on four datasets across multiple modalities, tasks, and backbones, demonstrating higher data‑efficiency in few‑shot scenarios and competitive performance, such as a +9.3 Dice point improvement in one‑shot segmentation on the M&Ms‑2 dataset. An in‑context dense prototype approach is also proposed, eliminating the need for downstream training.
arXiv:2602.16365v2 Announce Type: replace-cross Abstract: Flexible endoscopic continuum manipulators offer high dexterity and access to complex anatomy, but nonlinear hysteresis limits feedforward co...
arXiv:2511.16949v2 Announce Type: replace-cross Abstract: Dense 3D semantic occupancy perception is critical for mobile robots operating in pedestrian-rich environments, yet it remains underexplored...
The paper introduces SAM3-LoRA, a parameter‑efficient adaptation of the SAM3 segmentation foundation model using Low‑Rank Adaptation for multi‑class structural defect segmentation. It presents a supervision method that trains the model directly from COCO‑style instance segmentation by using category names as prompts, eliminating the need for prompt templates or learned embeddings. The authors also identify a failure mode where the model responds to any prompt due to positive‑prompt‑only annotations and resolve it with exhaustive hard‑negative prompting, achieving significant improvements in pixel IoU and instance recall on both a tunnel lining dataset and the Structural Defects Dataset.
The paper examines RGB‑infrared fusion for binary wildfire segmentation using UAV imagery on the FLAME3 dataset. It compares RGB and infrared baselines with three fusion strategies across U‑Net, DeepLabV3+, and SegFormer architectures. Results show thermal data dominates segmentation performance, and feature‑level fusion with transformer‑based models yields the best results.
The paper introduces the Hierarchical Semantic Distillation Network (HSDN), a method for compressing chain-of-thought reasoning in financial contexts while maintaining accuracy and logical coherence. HSDN uses semantic segmentation, dependency graph construction, dual encoder importance scoring, constrained segment selection, and local boundary rewriting to reduce the length of intermediate reasoning traces. Evaluated on the AFAC2025 benchmark, HSDN achieves 91.0% accuracy with a 68.4% compression rate, outperforming strong baselines in overall score and reasoning coherence.
CMRVision is a cardiac magnetic resonance (CMR) foundation model trained with DINOv3-style self‑supervised learning on 36 million multi‑center, multi‑sequence CMR images. It outperforms prior natural‑image, medical‑image, supervised, and CMR baselines on multi‑task segmentation (cine, LGE, mapping) and cine view classification, achieving Dice scores of 0.940–0.967 for LV and 0.855–0.905 for myocardium, and a zero‑shot Dice of 0.692 on unseen LGE long‑axis views. The model demonstrates robust cross‑view generalization and highest average accuracy (0.906) for cine view classification.
Scope3Trace is an evidence‑grounded information extraction framework that identifies and extracts Scope 3 greenhouse gas emissions from corporate sustainability reports. It combines PDF collection, OCR parsing, LLM‑assisted page localization, table reconstruction, and a hybrid rule‑LLM extraction process with evidence verification to produce interpretable, traceable emissions data. The authors also release a multimodal dataset of organization‑level Scope 3 disclosures extracted from diverse reports, demonstrating high accuracy in retrieving Scope 1‑3 totals and category‑level details.
arXiv:2609. 01064v1 Announce Type: cross Abstract: Reconstructing a damaged musical fragment is an inverse problem: the observed sequence contains partial information, while a raga encodes constraints limiting allowable completions.
The paper presents a semi‑supervised biomedical image segmentation method that uses a diffusion‑based teacher–student framework. The teacher is pretrained via unsupervised diffusion reconstruction and then co‑trained with a student, leveraging supervised labels and cross pseudo‑supervision on unlabeled data. A multi‑round extension generates multiple stochastic reconstructions to further refine pseudo‑labels, achieving competitive or superior results on several 2D and 3D biomedical datasets, especially when labels are scarce.
arXiv:2609.01530v1 Announce Type: new Abstract: Self-supervised pre-training via cross-view completion learns strong features for 3D vision from co-visible regions of image pairs. However, the refere...
arXiv:2609.00704v1 Announce Type: new Abstract: Functional tissue units (FTUs), including tertiary lymphoid structures (TLSs), blood vessels, and glands, encode localized immune, vascular, and epithe...
arXiv:2507.20881v3 Announce Type: replace Abstract: Endoscopic depth estimation is a critical technology for improving the safety and precision of minimally invasive surgery. It has attracted conside...
arXiv:2609.01514v1 Announce Type: cross Abstract: Historically, retrieving rainfall data from satellite imagery has been the domain of space agencies. However, in recent years, the development of che...
arXiv:2609.01598v1 Announce Type: new Abstract: Accurate segmentation of vascular structures in digital subtraction angiography (DSA) images remains challenging due to the thin, elongated, and branch...
arXiv:2509.25050v2 Announce Type: replace Abstract: Reinforcement Learning (RL) has emerged as a central paradigm for advancing Large Language Models (LLMs), where both pre-training and RL post-train...
arXiv:2609.01172v1 Announce Type: new Abstract: Monocular depth estimation has long stood as a fundamental challenge in computer vision, enabling a wide range of applications including 3D reconstruct...