Detection, segmentation, depth and recognition research, plus the vision backbones that keep displacing the last generation.
arXiv:2609.26662v1 Announce Type: new Abstract: Purposes: To characterize longitudinal retinal vascular changes in myopic children treated with orthokeratology (OK) or multifocal defocus lenses (Defo...
arXiv:2609.25627v1 Announce Type: cross Abstract: General-purpose robot control requires models to understand task intent, identify where to interact, capture how the scene evolves, and generate prec...
arXiv:2410.07421v2 Announce Type: replace Abstract: Instance segmentation is a core computer vision task with great practical significance. Recent advances, driven by large-scale benchmark datasets,...
arXiv:2603.11323v2 Announce Type: replace Abstract: The simplicity and effectiveness of UNet architectures make them ubiquitous in image restoration, segmentation, and diffusion models. They are ofte...
The ICDAR2026 Competition on Multimodal Reasoning over Documents in Multiple Domains introduced a new Visual Question Answering benchmark that tests reasoning over documents from eight distinct domains such as business reports, scientific papers, and engineering drawings. Twenty valid submissions from eight teams were evaluated, featuring approaches ranging from zero‑shot vision‑language models to multi‑agent ensembles and fine‑tuned multimodal systems. Results indicate that the most effective systems employ structured evidence extraction, retrieval, verification, and orchestration across multiple components rather than single‑pass prompting.
The paper investigates black-box privacy auditing for differentially private learning algorithms, focusing on DP‑SGD. It introduces a method that optimizes the auditor’s canary set using metagradient descent, improving empirical lower bounds on privacy parameters compared to prior canary designs. The approach is shown to be DP‑SGD agnostic and efficient, with optimized canaries for small models remaining effective for larger DP‑SGD models.
The paper introduces a 3D residual wavelet diffusion model for super‑resolving ultra low‑field MRI scans. By using a lossless wavelet reparameterisation, residual shifting, and domain randomisation, the method fits whole‑brain data on a single GPU, speeds up sampling, and generalises across scanners. It achieves volumetric accuracy comparable to leading regression approaches while producing per‑voxel uncertainty maps that reveal under‑determined regions and preserves disease‑relevant atrophy in cognitively impaired subjects.
The paper introduces Quality-Constrained Image Coding for Machines (ICM), which compresses images by treating a computer vision application as the primary observer while limiting human-observed quality to a specified target. By formulating joint compression and segmentation as a constrained optimization problem, the authors design penalty functions that steer the codec toward the desired visual quality, allowing remaining coding capacity to enhance machine performance. Experiments demonstrate significant bitrate savings—up to 22.82% over unconstrained joint optimization and 29.81% over a simple rate–distortion baseline—while maintaining target visual quality without added complexity.
Annual Earth‑observation embeddings, specifically Tessera, can encode wildfire disturbance signals well enough to map burned areas without needing curated fire‑specific imagery or dense time‑series analysis. In tests, linear models using a single Tessera embedding matched or outperformed paired pre‑ and post‑fire HLS imagery and post‑fire imagery alone, achieving high F1 scores for burn‑scar delineation and regional mapping. The approach successfully mapped all same‑year fires in benchmark scenes, recovered 97% of California burned area without California training data, transferred to European fires with high accuracy, and even estimated ignition timing within a 13‑day error margin. "whyItMatters":"The study demonstrates that pre‑trained annual embeddings can simplify and scale burned‑area mapping, reducing reliance on dense time‑series data and enabling more efficient wildfire monitoring."
The paper "End-to-End Visual Odometry with RNNs and Attention" presents a study of deep‑learning approaches to visual odometry (VO), proposing a novel temporal attention‑based model to enhance performance. It evaluates existing end‑to‑end VO methods and explores their effectiveness on hand‑held camera data, contrasting with the typical driving‑scene training sets. The work aims to improve VO accuracy in more dynamic and complex visual environments.
The paper presents a framework that builds a static point cloud prior map from past camera traversals, augmenting each point with DINOv3 semantic features. During runtime, a local prior patch is retrieved, encoded with a sparse voxel backbone, and fused with lifted multi‑view camera features in bird’s‑eye view. This fused representation is then used by sparse transformer heads to predict 3D objects and vectorized map elements, achieving improved performance on Argoverse 2 without requiring LiDAR for prior‑map construction or online inference.
arXiv:2605.00915v2 Announce Type: replace Abstract: Probing frozen vision transformers typically uses permutation-invariant aggregation (GAP or $\texttt{[CLS]}$), treating patch tokens as an unstruct...
arXiv:2609.22353v1 Announce Type: new Abstract: Mobile river monitoring robots must interpret obstacles and water boundaries that geographic waypoints alone cannot describe. On resource constrained p...
arXiv:2609.22620v1 Announce Type: new Abstract: Scanned mail, uploaded PDFs, and consolidated attachments often arrive as page streams that must be split into individual documents before downstream c...
arXiv:2609.24838v1 Announce Type: new Abstract: Medical agents increasingly combine general reasoning models with specialized clinical tools, yet their capabilities remain largely fixed by what clini...
arXiv:2609.25082v1 Announce Type: new Abstract: Quantum machine learning (QML) is increasingly recognized as one of the most promising near-term applications of quantum computing, viewed as a next-fr...
Moving6DPoSe is a multimodal database for monocular 6D pose estimation and segmentation of moving objects, comprising two subsets: real-world recordings (Moving6DPoSe‑R) and synthetic sequences (Moving6DPoSe‑S). It includes 16 scanned objects, 1,702 real and synthetic rosbags, and annotations for semantic segmentation, object detection, and monocular 6D pose estimation. Baseline results show that event-based representations outperform conventional RGB images for moving‑object segmentation, while monocular orientation estimation remains challenging.
arXiv:2609.26631v1 Announce Type: new Abstract: Accurate ground-based cloud classification is important for atmospheric monitoring, solar-energy forecasting, aviation weather assessment, and climate...
arXiv:2609.25067v1 Announce Type: cross Abstract: Self-supervised learning (SSL) has become an effective approach for learning visual representations without manual annotations. Among SSL approaches,...
arXiv:2609.25978v1 Announce Type: cross Abstract: Saliency maps are widely used to explain deep learning predictions in medical imaging, yet visually plausible explanations do not necessarily reflect...