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 87
DirCast: Live Esports Directing and Commentary with a Single Streaming Video-Language Model
A live esports broadcast needs a director who chooses which camera goes on air and a caster who talks over that choice, every second and without knowing what comes next.AudioLift: Audio-Driven Single Image to Full-Head Gaussian Avatar via Multi-view Video Generation
Existing 3D talking avatar methods mainly rely on parametric face models including 3DMM or FLAME, whose compact motion representations limit their ability to synthesize extreme expressions and to…See What I Need, Dream What I Want: A Navigation Foundation Model on a Self-Constructed Representation Space
What visual representation should a navigation policy act on?SyncVid: World-Equivariant Diffusion for Synchronized Video Generation
Generating multiple videos of a dynamic scene from a single reference video requires synthesizing both observed and unobserved content consistently across viewpoints.PaperScorer: How Predictable Is Paper Acceptance?
Automated research is largely evaluated by benchmark performance, but the value of research rarely reduces to a single score.PnP*: A certifiable solver for Perspective-n-Point
Estimating a camera pose from 3D-2D correspondences - Perspective-n-Point - is one of the most fundamental problems in computer vision.StackGen3D: Stable 3D Block Stack Generation from Multiview Silhouettes
Generating physically stable 3D structures from visual specifications requires resolving geometric ambiguity while accounting for physical interactions among objects.WorldMirror: Agentic Real-to-Sim Generation of Interactive Worlds from In-the-Wild Robot Demonstrations
Existing approaches for robot learning in simulation often require substantial manual effort to construct scenes and specify tasks, limiting training scalability and data diversity.SAGE: A hybrid vision-language and geometry framework for work-zone pathway prediction under temporary traffic control
Temporary traffic control redirects vehicles through work zones, requiring automated vehicles to connect an interpretation of the visible devices to a continuous passing path.SAGE: Sense-Aligned Multimodal Grounding Evaluation with Gloss-Augmented Reasoning
This paper introduces Sense-Aligned Grounding Evaluation (SAGE), a unified 10-candidate image-selection benchmark that reformulates VWSD, VerSe, and WikiDiverse into a shared term-centric protocol…EgoForesight: Effectively Scaling Policy Learning with Noisy Egocentric Actions
Scaling policy learning requires broad experience and reliable supervision.IFC-SSL-Bench: Benchmarking Self-Supervised Learning for Annotation-Efficient Multispectral Imaging Flow Cytometry
Imaging Flow Cytometry (IFC) generates large multispectral datasets, yet the need for expert annotations bottlenecks the development of supervised deep learning models.FSVL: Taxonomic Fast-Slow Vision-to-Language Collaborative Framework for Interpretable Confusable Fish Species Identification and Knowledge Generation in the Middle Yangtze River
The Yangtze River Basin is a critical region for freshwater biodiversity conservation.Scaling Transformer Energy-based Models For High Quality Image Synthesis
Energy-Based Models (EBMs) are a flexible class of generative models that decouple probabilistic modeling from the generation process.VisFlow: Interpretable Flow Matching for Visibility Reconstruction, Characterization, and Recognition
Methods for learning continuous representations, such as latent manifolds, are fundamental and ubiquitous in modern machine learning.StateBridge: Phase- and Track-Grounded Reasoning for Synthetic-to-Real Traffic Video Captioning and VQA
Traffic safety videos provide rich evidence for understanding interactions between pedestrians and vehicles, but synthetic-to-real evaluation makes this setting challenging because models must learn…Automated Nucleus Segmentation in Histology Images: An Attention U-Net Approach with Comprehensive Preprocessing and Inference Pipelines
In the area of digital pathology, nucleus segmentation is an essential step for quantitative analysis; however, high nuclear density and staining heterogeneity in histology images pose a great…PixGR: Pixel-Space Generative Decoding for Fast Feed-Forward 3D Reconstruction
We present PixGR, an efficient framework that integrates lightweight pixel-space generative modeling into feed-forward 3D Gaussian reconstruction to model scene uncertainty.Synthetic-to-Real Text-Based Person Anomaly Search via Multi-Model Retrieval Fusion and Cross-Encoder Reranking
Text-based person anomaly search requires a model to retrieve individuals from a large image gallery using natural-language descriptions of both appearance and behavior.LOCI: Localized Continuous Control for Multi-Subject Image Editing
Recent instruction-following image editors such as Flux.1-Kontext enable text-driven editing but lack fine-grained control over where and how much an edit is applied.