Visão Computacional

Blog Visão Computacional

DL-SLAM: Enabling High-Fidelity Gaussian Splatting SLAM in Dynamic Environments based on Dual-Level Probability

arXiv:2607.01860v1 Announce Type: new Abstract: Recent advances in 3D Gaussian Splatting (3DGS) have enabled significant progress in dense dynamic Simultaneous Localization And Mapping (SLAM). Prevailing methods typically discard predefined dynamic objects, ignoring that transiently static objects offer valuable geometric constraints for pose estimation. A recent work attempts to leverage this potential by employing per-pixel uncertainty maps to quantify the magnitude of motion. While this appro...

03.07.2026

Blog Visão Computacional

A Stereo Visual SLAM System Using Object-Level Motion Estimation and Geometric Filtering Based on Cross Disparity

arXiv:2607.02005v1 Announce Type: new Abstract: This paper presents OCD SLAM, a dynamic stereo visual SLAM framework that extends ORB-SLAM2 by jointly addressing dynamic objects and dynamic features in the scene. Usual visual SLAM systems operating in dynamic environments often fail in the presence of moving objects, due to the static-world assumption used in pose estimation and mapping. To address this predicament, we introduce a novel geometric approach based on the discrepancy between dispari...

03.07.2026

Blog Robótica & RL

VLA-Corrector: Lightweight Detect-and-Correct Inference for Adaptive Action Horizon

arXiv:2607.01804v1 Announce Type: new Abstract: Vision-Language-Action (VLA) foundation models have recently achieved strong progress in embodied intelligence. To reduce policy-call frequency while preserving temporal coherence, most generative policies adopt an action chunk mechanism, executing multiple future actions in an open-loop manner under a fixed action horizon. However, this "predict-then-blindly-execute" paradigm sacrifices closed-loop reactivity: in contact-rich physical interactions...

03.07.2026

Paper Visão Computacional

PixCon: Clean-Positive Contrastive Learning for Foundation-Model Semi-Supervised Segmentation

PixCon is a semi-supervised semantic segmentation framework that uses clean-positive pixel-contrastive learning with per-class memory banks to improve accuracy over existing method…

03.07.2026

Blog Visão Computacional

Stop Pretending Social Robots Are Inevitable

arXiv:2607.00142v1 Announce Type: new Abstract: This paper takes issue with the recent themes of both the RO-MAN and the HRI conferences for their portrayal of a future human-robot society as inevitable. The focus is on discussing how such statements ultimately shape research. By treating a future human-robot society as a fait accompli, license is given for user studies to imagine any scenario they like, no matter whether it has any ecological relevance, and to emphasise the scenario design over...

02.07.2026

Blog Visão Computacional

Segmenting, Fast and Slow: Real-Time Open-Vocabulary Video Instance Segmentation with Dual-Path Processing

arXiv:2607.00124v1 Announce Type: new Abstract: Object-centric models inspired by DETR have become the dominant paradigm for open-vocabulary video instance segmentation (OV-VIS). While recent efforts have reduced the computational cost of pixel decoding, textual modality fusion, and object decoding to make these architectures more suitable for mobile devices, real-time on-device inference at high frame rates remains an open challenge. In this paper, we introduce SegFS, a dual-stream fast-slow fr...

02.07.2026

Blog LLMs & Texto

Decompose, Compare, and Decide: Multimodal LLMs are Implicit Few-Shot Learners

arXiv:2607.00125v1 Announce Type: new Abstract: Multimodal Large Language Models (MLLMs) have demonstrated remarkable abilities when analyzing images, yet translating these capabilities to few-shot image classification remains challenging. To bridge this gap, we present DeCoDe, a simple yet effective technique that enables off-the-shelf MLLMs to act as strong few-shot classifiers without any additional training. Our approach builds on the idea of few-shot classification as a set of pairwise imag...

02.07.2026

Blog Geração de Imagem

Joint Medical Image Enhancement and Segmentation with Diffusion-based Symbiotic Information Interaction

arXiv:2607.00058v1 Announce Type: new Abstract: Image quality is critical for accurate medical diagnosis. However, MRI, CT, and ultrasound images are often of low resolution and quality due to cost constraints, complicating the visualization of key anatomical structures and lesions. While such limitations are common in practice, traditional methods treat image enhancement as a separate preprocessing step, failing to fully leverage its potential synergy with image segmentation. To address this, w...

02.07.2026

Blog LLMs & Texto

Representation as a Bottleneck for Mechanistic Interpretability: The Manifestation Unit Protocol

arXiv:2607.00089v1 Announce Type: new Abstract: Mechanistic interpretability has produced a rich inventory of component-level analyses that characterise what neural-network components encode and how they interact. Their outputs, however, are not easily reusable: selectivity tables, circuit diagrams, and feature lists remain locked in per-study notebooks - non-composable, not queryable in natural language, and not directly actionable for downstream audit or intervention. We study the representati...

02.07.2026

Blog Visão Computacional

Does Your ViT Still Need U-Net for Segmentation?

arXiv:2607.00223v1 Announce Type: new Abstract: Medical image segmentation is dominated by U-Net-style encoder-decoder architectures. Vision Transformers (ViTs) overcome the limited receptive field of convolutional networks through self-attention, enabling modeling of long-range dependencies. Early ViT-based segmentation methods typically retained U-Net-style decoders because pretrained ViT representations were insufficient to support accurate dense prediction. Recent advances in large-scale pre...

02.07.2026

Blog LLMs & Texto

Watermarking for Proprietary Dataset Protection

arXiv:2607.00325v1 Announce Type: new Abstract: A growing body of literature suggests that training data membership inference problems are fundamentally hard tasks in modern language modeling settings. We argue that output watermarking techniques are the right gadget to make training membership tests for generative models more tractable, based on prior results showing that language models exhibit residual watermark "radioactivity" under partially watermarked training datasets. We pit a watermark...

02.07.2026

Blog LLMs & Texto

AEGIS: A Multi-Task Joint-Embedding Predictive Architecture for Mammography

arXiv:2607.00277v1 Announce Type: new Abstract: We present Aegis, a joint-embedding predictive architecture for breast cancer detection and density assessment in mammography. We train three Vision Transformer variants (Small/Base/Large) using self-supervised joint-embedding predictive architecture (JEPA) pre-training on 71,103 studies from 14 clinical sites, followed by supervised fine-tuning with progressive resolution scaling up to 2048x1536. On a curated 785-study test set, our largest model ...

02.07.2026