Computer Vision

Reolink unveiled the OMVI 2i Ultra security camera at IFA 2026, featuring dual cameras that combine an 8MP ultra-wide view with a 5MP pan-and-tilt camera to track subjects beyond the wide camera's field of view. The comp…

ApplyOnce, a local-first job application autofill extension formerly codenamed FastApply, released version 0.2 with layout-aware resume parsing, on-device OCR for scanned resumes, resume re-import, and an optional on-dev…

StabRise has released @stabrise/scaledp, a document-AI pipeline that runs OCR entirely in the browser via onnxruntime-web, eliminating the need for server-side processing. The new PaddleRecognizer stage decouples text de…

A developer comparing four background-removal paths on a challenging test image found that the largest AI model left 5.73% of the frame at alpha 1–8, an invisible residue on checkerboard that reappears on white. The non-…

At IFA 2026, Reolink unveiled the Home Hub 2, OMVI 2i Ultra, and an upgraded ReoNeura AI system, introducing subscription-free local video search and custom detection features. The new products aim to enhance smart home …

Plyxo Community Edition has released an open-source Visual CRO engine that uses multimodal vision models to audit webpages for UX friction, drawing bounding boxes over problem areas and generating Tailwind CSS fixes. The…

Researchers propose Laplacian Frequency Hierarchies, a plug-and-play scheme for 3D Gaussian Splatting training that reduces active Gaussians by archiving lower-frequency fields, achieving average speedups of 1.73x and 1.…

Researchers propose TRIM (Trigger Removal by Identifying Manipulated Regions), a black-box defense that detects and removes backdoor triggers in deep neural networks at inference time without requiring model internals, t…

A new reliability-aware geometry distillation framework enables RGB-D salient object detection without using dataset-provided depth during training or inference, achieving the best or tied-best result in 26 of 36 metric-…

Researchers introduced PointGT, a point-based 3D representation enabling simultaneous geometry and texture editing, addressing limitations of existing volumetric methods like 3D Gaussian Splatting that struggle with geom…

Researchers introduced CulturalMenuBench, a benchmark of 4,870 items across 10 languages and 18 regions, revealing that multimodal language models scoring above 94% on standard food recognition tasks drop to at most 56% …

Researchers introduced Exemplar, a few-shot segmenter that fuses a frozen DINOv3 backbone with classical native-resolution filter responses in a single lightweight head, achieving a mean score of 0.782 across eleven biom…

Researchers propose CoverPruner, a training-free visual token pruner for vision-language models (VLMs) that frames pruning as Representational Coverage Maximization (RCM), ensuring each removed token is represented by a …

Researchers present a unified computational approach to tensor-based morphometry that detects brain surface shape differences between clinical groups from magnetic resonance images, combining surface modeling, smoothing,…

Researchers propose P-CORE, a self-supervised method for point-based neural editing that improves robustness to large deformations by enforcing surface consistency before and after random deformations. The method, integr…

Researchers proposed an ensemble-based self-taught learning approach using convolutional autoencoders for parking space classification, achieving 93% to 96% accuracy on the PKLot and CNRPark benchmarks under cross-datase…

Researchers introduced ProgResViT, an input-adaptive Vision Transformer that progressively increases input resolution and model width across rounds, terminating early when predictions are confident. Applied to DeiT, Prog…

Researchers propose FreNet, a feature reconfiguration framework with visual priors, that outperforms state-of-the-art methods on 9 medical image segmentation benchmarks across three imaging modalities, achieving Dice imp…

An independent developer building a creator asset tool added an image-to-video button that turns a single outfit image into an eight-second clothing showcase. Using GPT Image 2 via hiAPI for the still and Seedance 2.5 im…

Ant Group open-sourced LingBot-Vision, a family of self-supervised Vision Transformer backbones for dense spatial perception, with models ranging from ViT-S/16 to a 1.1B-parameter ViT-g/16, released on Hugging Face and M…