cs.CV
PulseAugur coverage of cs.CV — every cluster mentioning cs.CV across labs, papers, and developer communities, ranked by signal.
17 day(s) with sentiment data
-
New AI model NerveDetNet detects nerves beneath tissue using OCT
Researchers have developed a novel label-free framework for detecting peripheral nerves beneath intact tissue using optical coherence tomography (OCT) and a deep learning model called NerveDetNet. This system integrates…
-
New framework estimates camera platform motion with arcsecond accuracy
Researchers have developed a novel framework for estimating the relative motion of camera platforms used in vision measurement, particularly in scenarios with incomplete or absent control fields. This method directly ca…
-
New lossless compression method for medical images bypasses deep learning
Researchers have developed a new method for lossless compression of volumetric medical images that does not require deep neural networks or external training data. This approach, called the tri-plane context tree (TCT) …
-
EvoTale framework enables continual character customization for story worlds
Researchers have developed EvoTale, a new framework designed for continually customizing characters within expanding story worlds. This system addresses the challenge of integrating new characters without disrupting exi…
-
New method improves 3D tree modeling and biomass estimation with foliage
Researchers have developed a new method for 3D tree modeling and biomass estimation from point clouds, specifically addressing the challenges posed by foliage. This approach utilizes a topology-driven foliage suppressio…
-
New method iteratively learns image correspondences in real-time
Researchers have developed a new iterative method for learning point correspondences between image sequences, even when the 3D geometry and projection distortions are unknown. This approach optimizes mappings using Neym…
-
AI research questions reliability of distance-based estimation in medical imaging representations
A new research paper published on arXiv explores the reliability of distance-based estimation methods for AI-generated representations, particularly in the context of medical imaging. The study found that while disentan…
-
New distillation method improves autoregressive video generation
Researchers have developed Context-Matched Distillation (CMD), a novel framework for improving autoregressive video generation models. CMD aligns the teacher model's supervision with the causal context available to the …
-
CableDex system estimates industrial cable length from single photo
A new computer vision system called CableDex has been developed to accurately estimate the length of industrial cables on reels from a single mobile phone photograph. This system utilizes camera calibration, instance se…
-
Mask R-CNN model enables tooth detection from smartphone photos
Researchers have developed a new system called TLNM that uses Mask R-CNN to detect, number, and segment teeth from smartphone photographs. This pipeline incorporates a masked gray-world white-balancing algorithm and an …
-
New research advances video anomaly detection with agentic reasoning and federated learning
Multiple research papers are exploring advanced techniques for Video Anomaly Detection (VAD), moving beyond traditional methods. One approach, "Glance then Scrutinize" (GtS), uses textual guidance for anomaly grounding …
-
New OmniRouting benchmark tests LLMs on complex PCB routing tasks
Researchers have introduced OmniRouting, a new benchmark designed to test the spatial reasoning capabilities of large language models (LLMs) in the complex domain of printed circuit board (PCB) routing. The benchmark in…
-
Client-side image editing controls cosmetic surgery previews accurately
A new research paper explores methods for controlling image-editing APIs to accurately preview cosmetic surgery procedures. The study found that client-side techniques, such as using masks and composites, can effectivel…
-
FairForensics model enhances deepfake detection fairness and generalization
Researchers have developed FairForensics, a novel vision-language model designed to improve the fairness and generalization of deepfake detection. This model addresses the issue of demographic bias in existing detectors…
-
New research advances 3D part decomposition with material and topology awareness · 2 sources tracked
Two new research papers, PartMat and Hi-TOPS, introduce novel methods for 3D part decomposition. PartMat focuses on material-aware decomposition using a single global latent representation and a diffusion model, aiming …
-
New research offers advanced methods for deformable medical image registration
Two new research papers explore advancements in deformable image registration (DIR) for medical imaging. One paper introduces an accessible implementation of the pTVreg method, enhanced with a Bayesian optimization fram…
-
New multi-modal ReID framework enhances semantic awareness and feature alignment
Researchers have developed a new framework for multi-modal object Re-Identification (ReID) that addresses challenges in exploiting semantic priors and modeling global-local representations. The proposed method incorpora…
-
Deep Learning Applied to Surgical Gauze Segmentation in Minimally Invasive Surgery
Researchers have explored the application of deep learning techniques for segmenting surgical gauze in minimally invasive abdominal surgeries. This study addresses the challenge of data scarcity by using an in-house dat…
-
New ID-Guard framework combats facial manipulation by disrupting key features
Researchers have developed ID-Guard, a universal framework designed to combat facial manipulation by disrupting identifiable features in manipulated images. This system uses an encoder-decoder network to generate transf…
-
Endo-NeRF++ enhances surgical scene reconstruction with uncertainty awareness
Researchers have developed Endo-NeRF++, an advanced neural rendering framework designed to improve the reconstruction of dynamic surgical scenes. This new system addresses challenges like tissue deformation, occlusions,…