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 135
Q-MAGIC: Quad-only Mesh Autoregressive Generation via Singularity-Aware Circular Relative Offset Tokenization
Autoregressive models have proven effective for triangular mesh generation by transforming it into predicting the next face, converting the non-differentiable connectivity prediction into a sequence…Computational compressive imaging reconstruction with a simulated-annealing-based Ising solver
Computational compressive imaging, such as single-pixel imaging and lensless imaging, is a promising imaging technique, enabling the reconstruction of objects from under-sampled measurements through…FPV-CRASH: A Dataset for Offline Crash Moment Localization in Drone First-Person-View Videos
Crash Moment Localization aims to localize the major physical impact that interrupts controlled flight in an onboard first-person-view (FPV) video recorded by a drone, thereby providing a temporal…LiFi: LiDAR Generation from Multi-View Images via Geometric and Semantic Collaborative Guidance
Generating LiDAR point clouds from multi-view camera images is a valuable task with applications in controllable data synthesis, cross-modal simulation and various perception tasks.StateCraft: Augmenting Video World Models with Abstract-State Reasoning
Video world models aim to simulate complex environments with realistic appearance and dynamics.Improving Category-Aware Active Domain Adaptation via Uncertainty-Guided Region Coverage
Active domain adaptation researches focus on alleviating the annotation cost, which comprises source data and target data labelling, as well as enhancing the performance of unsupervised domain…PhyMetric: Diagnosing Physical Plausibility in Text-to-Video Generation via Scene-Level QA
Text-to-video (T2V) generation models can produce visually realistic videos that nevertheless violate the physical consequences implied by the prompt and scene.What Matters for World Modeling in Vision-Language-Action Models?
Integrating world models into Vision-Language-Action models (VLAs) has emerged as a promising direction, enabling policies to anticipate future dynamics beyond reactive observation-to-action mapping.DarKnight: Retrieval-Guided Agentic Framework for Breaking Dark Web CAPTCHA Gates
Cyber Threat Intelligence (CTI) investigators who monitor dark web marketplaces for leaked credentials and breach listings must pass the diverse CAPTCHAs that operators deploy to block automated…VisibilitySplat: Ray-Traced Occlusion for Relighting with 3D Gaussian Splatting
We address inverse rendering with 3D Gaussian Splatting (3DGS) by introducing explicit visibility modeling for relighting as well as material and light decomposition.DeltaStreamer: Towards Human-Like Agentic Streaming Video Understanding
We propose DeltaStreamer, a novel agentic framework for streaming video understanding inspired by how humans observe, remember, and investigate.OmniPoser: Flexible Human Motion Recovery in the Wild with Masked Flow Matching
Recovering 3D human motion from sparse wearable sensors is challenging due to the inherent noise, occlusion, and instability of real-world tracking signals.CoDy: Codec Dynamics as Complementary Priors for Unsupervised Temporal Action Localization
Unsupervised temporal action localization (UTAL) aims to identify action categories and localize their temporal boundaries without annotation supervision.BluePixel: Toward Native 4K Agentic Image Editing
Instruction-driven image editing has reached native 4K, yet how such editors are trained remains undisclosed, and pretraining one from scratch is beyond most teams.On the Limits of Representation-Based Test-Time Adaptation for Multimodal LLMs
Vision-language models suffer significant accuracy drops under common corruptions.Multimodal Medical Image Parsing with Task-Specific Low-Rank Adapters
Adapting a single vision-language model to medical image parsing requires training choices that reflect the demands of each task.CARD: Closing the Teacher-Student Loop for Adversarial Robustness Distillation
Adversarial robustness distillation typically treats a robust teacher as a fixed knowledge source and transfers robustness to a compact student in a one-way manner.Quantifying Annotation Agreement in Object Detection with Optimal Transport
Reliable validation of machine learning models is a crucial step in designing robust and trustworthy systems.SAM3RL: Memory Control via Reinforcement Learning for Visual Object Tracking
Segment Anything Model 3 (SAM 3) is a foundation model for image and video segmentation that sets the state of the art in visual object tracking.Instruction Mining From Images: Constructing a Synthetic Dataset for Multimodal Learning ILSP DCVLR Competition Submission
This work presents a compact and reproducible pipeline for synthesizing and curating image-based instruction-response pairs for DCVLR.