Computer Vision RSS Feeds

Directory166 computer vision feeds · 89 articles

Latest

Computer Vision articles

FeyNoBg: Open-Source Background Removal Model Achieves State-of-the-Art Results Across Eight Benchmarks

FeyNoBg beats or matches the current leaders across eight benchmarks. Alongside the model, we're releasing NoBg. The library we used to train it.

technologyprogrammingopen source

usefeyn.com·Hacker News: Front Page·1mo ago·8 min read

Inside Reka Labs' Data Pipeline for Training World Models at Petabyte Scale

Insighttechnologyprogramming

Shared by @DaniYogatama ↗

reka.ai1mo ago

OpenAI's GPT-5.6 Sol: Benchmarking vision capabilities across detection, OCR, and extraction tasks

Insighttechnologyscience

Shared by @skalskip92 ↗

blog.roboflow.com1mo ago

Wan-Dancer: A hierarchical AI framework enabling minute-scale coherent music-to-dance video generation

Generating long-duration, high-definition, and rhythmically synchronized dance videos directly from music remains a significant challenge, primarily due to the temporal constraints of current diffusion models, which typically fail beyond 20 seconds. Exist

Insighttechnologyscience

Shared by @ai-firehose.column.social ↗

arxiv.org1mo ago

fal Releases Ideogram 4 Fast: A Speed-Distilled Text-to-Image Model for FP4 Inference

We’re on a journey to advance and democratize artificial intelligence through open source and open science.

technologyprogrammingcomputer visionhuggingface.co·@fal·1mo ago·4 min read

DeepLabCut: A Toolbox for Markerless Animal Pose Estimation

DeepLabCut™️ is a toolbox for state-of-the-art markerless pose estimation of animals performing various behaviors. As long as you can see (label) what you want to track, you can use this toolbox, as it is animal and object agnostic. Read a short developme

technologysciencecomputer visiondeeplabcut.github.io·@zebrafishrock.bsky.social·1mo ago·11 min read

RepStandard uses on-device computer vision to automatically count bodyweight exercise reps

Most fitness apps make you manually log sets or need a wearable to guess your effort. RepStandard's camera does the counting for you - squats, push-ups, sit-ups, and plank, tracked in real time via on-device pose detection (nothing leaves your phone). It

Producttechnologyhealthfitness

Product Hunt — The best new products, every day·1mo ago·2 min read

Veryfi Launches On-Device Field Detection for Real-Time Receipt Validation at Capture

Producttechnologybusiness

Product Hunt2mo ago

LILAC: A Layer-Based Framework for Multi-Concept Customization of Diffusion Models Without Joint Training

Personalizing text-to-image diffusion models to render several specific subjects in a coherent image remains challenging: the model must preserve each subject's identity while keeping the scene spatially and visually coherent. Methods that fuse independen

Insighttechnologyscience

Shared by @ai-firehose.column.social ↗

arxiv.org2mo ago

DataComp-VLM: A Benchmark Reveals Data Mixing Beats Filtering for Vision-Language Model Training

Building performant Vision-Language Models (VLMs) requires carefully curating large-scale training datasets, yet the community lacks systematic benchmarks for evaluating such curation strategies. We introduce DataComp for VLMs (DCVLM), a benchmark for con

Insighttechnologyscience

Shared by @lschmidt3 ↗

arxiv.org2mo ago

Group3D: MLLM-Driven Semantic Grouping for Open-Vocabulary 3D Object Detection (ECCV 2026) - GitHub Repository

Codetechnologyartificial intelligence

Shared by @_akhaliq ↗

github.com2mo ago

EPIC-Contact and HOPformer: A Dataset and Model for In-the-Wild Egocentric 3D Hand-Object Pose Estimation

technologyscience

Shared by @chris_j_paxton ↗

sid2697.github.io2mo ago

Using Vision-Language Models to Segment Robot Demonstration Videos into Subtask Annotations

Insighttechnologyscience

macrodata.co2mo ago

ArtiFixer: Using Auto-Regressive Diffusion Models to Improve 3D Reconstruction Quality

ArtiFixer: Enhancing and Extending 3D Reconstruction with Auto-Regressive Diffusion Models

Insighttechnologysciencecomputer visionnvda.ws·@NVIDIAAI·2mo ago·5 min read

Krea 2 (K2): Technical Report on Open-Weights Text-to-Image Foundation Models

Insighttechnologyart

krea.ai2mo ago

Signspell: Open-source Python package for real-time ASL fingerspelling recognition from webcam

Producttechnologyprogramming

Product Hunt2mo ago

Deep learning model classifies natural habitats from ground-level photographs with strong accuracy

Insighttechnologyscience

Shared by @plosone.org ↗

plos.io2mo ago

3D LiDAR Object Detection for Autonomous Driving: Training a Keypoint Feature Pyramid Network on the KITTI 360 Vision Dataset

Newstechnologyscience

Shared by @LearnOpenCV ↗

learnopencv.com2mo ago

NVIDIA Developer Forums24

SentiSight.ai1

Roboflow1

PyImageSearch4

e-con Systems3

PixLab133

FeyNoBg: Open-Source Background Removal Model Achieves State-of-the-Art Results Across Eight Benchmarks

Inside Reka Labs' Data Pipeline for Training World Models at Petabyte Scale

OpenAI's GPT-5.6 Sol: Benchmarking vision capabilities across detection, OCR, and extraction tasks

Wan-Dancer: A hierarchical AI framework enabling minute-scale coherent music-to-dance video generation

fal Releases Ideogram 4 Fast: A Speed-Distilled Text-to-Image Model for FP4 Inference

DeepLabCut: A Toolbox for Markerless Animal Pose Estimation

RepStandard uses on-device computer vision to automatically count bodyweight exercise reps

Veryfi Launches On-Device Field Detection for Real-Time Receipt Validation at Capture

LILAC: A Layer-Based Framework for Multi-Concept Customization of Diffusion Models Without Joint Training

DataComp-VLM: A Benchmark Reveals Data Mixing Beats Filtering for Vision-Language Model Training

Group3D: MLLM-Driven Semantic Grouping for Open-Vocabulary 3D Object Detection (ECCV 2026) - GitHub Repository

EPIC-Contact and HOPformer: A Dataset and Model for In-the-Wild Egocentric 3D Hand-Object Pose Estimation

Using Vision-Language Models to Segment Robot Demonstration Videos into Subtask Annotations

ArtiFixer: Using Auto-Regressive Diffusion Models to Improve 3D Reconstruction Quality

Krea 2 (K2): Technical Report on Open-Weights Text-to-Image Foundation Models

Signspell: Open-source Python package for real-time ASL fingerspelling recognition from webcam

Deep learning model classifies natural habitats from ground-level photographs with strong accuracy

3D LiDAR Object Detection for Autonomous Driving: Training a Keypoint Feature Pyramid Network on the KITTI 360 Vision Dataset