AI & Machine Learning · Computer Science & AI
Computer Vision
The newest papers in Computer Vision that ReadSearch has read, newest first. Each links to its own page, with its authors, date, where it was published and the original.
The newest 5,000 papers, from 29 September 2026 to 5 November 2026: 4,999 arXiv preprints and 1 OpenAlex record.
Get the few papers worth your time in Computer Vision every morning.
Follow Computer Vision and ReadSearch reads its new papers each day, then brings you the few worth reading, each with its key finding in a sentence.
Newest papers, page 181
Reference-Free Food Volume Estimation from Egocentric Stereo Video
Current stereo vision-based approaches for food portion estimation are hindered by the user burden of using a mobile phone to capture multiple images or placing a reference object in the scene for…Kernelized Parameter Sensitivity Atlases for Amortized Conditional Interpretability
Gradient-based attribution provides input-specific information about model parameters, but computing it via backpropagation for many samples is expensive, while static importance scores discard…Shift-Aware Identity-Guided Latent Refinement for Referring Audio--Visual Segmentation
Referring Audio--Visual Segmentation (Ref-AVS) is an emergent multimodal task requiring the precise identification and segmentation of a specific object based on a natural language expression…Domain Adaptation of SAM 2.1 for Building-Component Segmentation in Image-Based 3D Reconstruction
3D reconstruction of building components using image-based scanning requires appropriate segmentation of the objects in the 2D building images.Spend Where It Matters: Particle Search with MH Refinement for Budget-Constrained Audio-Visual Alignment
Reward-guided inference-time alignment can improve joint audio-visual generation, but optimizing multiple alignment objectives requires many expensive model evaluations, making existing methods…Pristine Models
Training on broad, unfiltered data enables high-quality image generation, but can also teach models concepts that should not be generated; restricting the training data ensures safety, but reduces…Human Pose Estimation by Probabilistic Mixtures of Gaussian and Uniform Distributions
Despite advancements in sub-pixel decoding, modern Human Pose Estimation (HPE) architectures remain constrained by deterministic coordinate extraction from discrete heatmaps, which systematically…Scenes as an Attack Surface: Uncovering Scene-Grounded Safety Failures in MLLMs
Existing jailbreak attacks have exposed serious safety weaknesses in multimodal large language models (MLLMs).RePrior: Measurement-Reconciled Prior Correction for Sparse-View CBCT Reconstruction
Sparse-view cone-beam computed tomography (CBCT) is severely under-constrained by limited X-ray projections.Temporal Diffusion Bridge Model for Vessel Extraction Using Physics-informed Synthetic Data
Accurate artery extraction from X-ray coronary angiography (XCA) is essential for coronary artery disease diagnosis and intervention.Pooling Representation Autoencoders for Efficient Diffusion
Representation Autoencoders (RAEs) generate images from pre-trained visual fea- tures, but their dense token grids make generative modeling expensive.Adaptive Visual Token Reduction for Accelerated Image Understanding
Large Vision-Language Models achieve strong VQA performance, but processing high-resolution, information-rich images requires substantial computation, motivating visual token reduction.PhyDiCT: Plug-and-Play CT Reconstruction from Sparse X-Rays via Differentiable Rendering and Strong Priors
Reconstructing 3D Computed Tomography (CT) images from a few X-ray projections is a highly ill-posed inverse problem due to the loss of volumetric information.Hardware-aware Calibrated Clustered Attention for Efficient Visual Geometric Transformers
The Visual Geometry Grounded Transformer (VGGT) marks a significant leap forward in 3D scene reconstruction, as it is the first model that directly infers all key 3D attributes (camera poses…EM-SNN: Efficiently Modulated Spiking Neural Network for Remote Sensing Image Dehazing
Although spiking neural networks (SNNs) provide an energy-efficient alternative to artificial neural networks (ANNs), their application to remote sensing image dehazing remains limited.LeCuration: A Tiny World Model as a Data Curation Multi-Tool
Many applications of physical AI run within finite or closed physical worlds with a limited set of physical laws governing object behavior.FaceKit: a Toolkit for Interpretable Facial Phenotyping, Synthetic Image Generation and Privacy Analysis in Rare Diseases
Many rare genetic diseases are associated with recognizable craniofacial features.emg2face: Expressive Facial Animation with High-Density Surface EMG
Facial movements convey subtle and important information that is critical for human social communication.Kuration SDK: Addressing the Virtual2Real Gap via Data Curation
Benchmarks for measuring the quality of action-conditioned world models are still evolving and shifting away from visual similarity-based metrics to action-semantic and physically-grounded metrics.Why VLMs Miss Small Objects, and When Zooming In Is Safe
Vision-language models (VLMs) often miss small objects in large images.