Visão Computacional

Blog Robótica & RL

Deployment-Ready UWB Localization for Industrial Ground Robots with Automatic Anchor Calibration and Terrain-Aware Fusion

arXiv:2607.15807v1 Announce Type: new Abstract: Ultra-Wideband (UWB) ranging has become a viable option for industrial Autonomous Mobile Robot (AMR) localization due to improved accuracy and low cost. However, real-world deployments remain limited by two recurring challenges: calibrating static anchors can be time-consuming and error-prone, and integrating UWB with existing onboard sensors requires careful design to ensure robust and consistent pose estimation. Addressing these challenges, this ...

20.07.2026

Blog Visão Computacional

Geometric Distillation from Rectified Stereo: Leveraging Epipolar Cues for Monocular Depth

arXiv:2607.15600v1 Announce Type: new Abstract: Monocular depth foundation models have demonstrated remarkable generalization capabilities across diverse environments. However, they continue to struggle with metric depth estimation in diverse environments. This limitation stems from the inherent scale ambiguity of single-view inference, leading to misaligned scale predictions even when the relative geometry is accurate. Conversely, recent multi-view foundation models leverage cross-view cues to ...

20.07.2026

Blog Visão Computacional

Partial Information Decomposition as a Multi-Contrast 3D MRI Selection Strategy for Resource-Constrained Deep Neural Network Training in Brain Tumor Segmentation

arXiv:2607.15396v1 Announce Type: new Abstract: Multi-contrast 3D MRI segmentation can be computationally demanding when all available sequences are used. We evaluate a pre-training Partial Information Decomposition framework that ranks input pairs according to their redundant, unique, and synergistic information about regional tumor burden and selects the highest-ranked pair for downstream training. Applied to T1n, T1c, T2w, and T2-FLAIR MRI, the framework selected T1c+T2-FLAIR. We then trained...

20.07.2026

Blog Visão Computacional

Google Deepmind argues video generators already contain the world models computer vision has been missing

Google Deepmind's GenCeption repurposes a video generator for classic vision tasks such as depth estimation and segmentation, matching state-of-the-art systems with far less training data. The model trained almost entirely on synthetic videos. Its results add to the debate over whether video generators already contain a kind of universal world model. The article Google Deepmind argues video generators already contain the world models computer vision has been missing appeared first on The Decoder...

19.07.2026

Blog LLMs & Texto

Kimi K3 vs DeepSeek V4 Pro vs GLM-5.2: Open Trillion-Scale MoE Models Compared on Benchmarks, License, and Serving Cost

Three open MoE flagships face off on measured intelligence, MIT versus Modified MIT weights, and real serving cost The post Kimi K3 vs DeepSeek V4 Pro vs GLM-5.2: Open Trillion-Scale MoE Models Compared on Benchmarks, License, and Serving Cost appeared first on MarkTechPost .

19.07.2026

Editorial Visão Computacional

VideoChat3: o modelo de vídeo de 4B que bate GPT-5 e Gemini no que eles não fazem bem

Um modelo aberto de 4 bilhões de parâmetros, criado por pesquisadores da Universidade de Nanjing e do Shanghai AI Laboratory, superou modelos proprietários em tarefas de percepção temporal fina — o tipo de vídeo que exige entender quando algo aconteceu, não só o que aconteceu.

18.07.2026

Paper LLMs & Texto

VideoChat3: Fully Open Video MLLM for Efficient and Generalist Video Understanding

Recent advances in video understanding have spanned motion, long video, and streaming interaction, driving this field toward real-world applications.

16.07.2026 ·▲ 154

Paper Robótica & RL

Beyond Entropy: Correctness-Aware Advantage Shaping via Contrastive Policy Optimization

Reinforcement learning with verifiable rewards (RLVR) commonly uses entropy for advantage shaping.

16.07.2026 ·▲ 5

Blog Geração de Imagem

Rumo à desmistificação da criatividade dos modelos de difusão

Algoritmos e Teoria

15.07.2026

Dataset Dados & Embeddings

uv-scripts/ocr

Dataset em destaque no Hugging Face — 2.4 mil downloads. OCR UV Scripts Part of uv-scripts — self-contained UV scripts you run on Hugging Face Jobs in one command.

15.07.2026 ·↓ 2424

Blog Visão Computacional

Os EUA estão avançando na segurança da IA por meio de ações estaduais e federais

A OpenAI apresenta uma abordagem de "federalismo reverso" para a governança da IA, na qual leis estaduais ajudam a construir um arcabouço nacional para uma IA segura e democrática.

15.07.2026

Editorial Visão Computacional

O meio do documento é onde os modelos se perdem

Um benchmark novo submete oito modelos de visão e linguagem a relatórios de 51 páginas e encontra um padrão desconfortável: a informação que está no miolo do documento é sistematicamente pior lida do que a do começo ou do fim. A queda chega a 18 pontos.

15.07.2026