Chest X-ray (CXR) segmentation is an important step in computer-aided diagnosis, yet deploying large foundation models in clinical settings remains challenging ...
Due to the large footprint of pixels in remote sensing imagery, hyperspectral unmixing (HU) has become an important and necessary procedure in hyperspectral ima...
As sports training becomes more data-driven, traditional dart coaching based mainly on experience and visual observation is increasingly inadequate for high-pre...
VisiPrint: AI‑Powered Aesthetic Previews for 3D‑Printed Objects Designers, makers, and other creators often use 3D printing to rapidly prototype a wide range o...
Modeling scenes using video generation models has garnered growing research interest in recent years. However, most existing approaches rely on perspective vide...
Video diffusion models exhibit emergent reasoning capabilities like solving mazes and puzzles, yet little is understood about how they reason during generation....
AI-assisted coding has rapidly reshaped software practice and research workflows, yet today's models still struggle to produce correct code for complex 3D geome...
Camouflaged object detection (COD) aims to identify targets that are highly blended with their backgrounds. Recent works have shown that the optical characteris...
Augmented reality (AR) devices with head mounted displays (HMDs) facilitate the direct superimposition of 3D preoperative imaging data onto the patient during s...
Multimodal deep learning has improved prognostic accuracy for brain tumours by integrating histopathology and genomic data, yet the contribution of volumetric M...
Understanding how brain structure and function interact is key to explaining intelligence yet modeling them jointly is challenging as the structural and functio...
Surgical video understanding is essential for computer-assisted interventions, yet existing surgical foundation models remain constrained by limited data scale,...
Surgical procedures are inherently complex and risky, requiring extensive expertise and constant focus to well navigate evolving intraoperative scenes. Computer...
Early identification of adolescents at risk for substance use initiation (SUI) is vital yet difficult, as most predictors treat connectivity as static or cross-...
Automated radiology report summarization aims to distill verbose findings into concise clinical impressions, but existing multimodal models often struggle with ...
Always-on edge cameras generate continuous video streams where redundant frames degrade cross-modal retrieval by crowding correct results out of top-k search. T...
Backdoor attacks on federated learning (FL) are most often evaluated with synthetic corner patches or out-of-distribution (OOD) patterns that are unlikely to ar...
Recent image generation models have shown strong capabilities in generating high-fidelity and photorealistic images. However, they are fundamentally constrained...
Synthesizing human motion has advanced rapidly, yet realistic hand motion and bimanual interaction remain underexplored. Whole-body models often miss the fine-g...
Acquiring labeled datasets for 3D human mesh estimation is challenging due to depth ambiguities and the inherent difficulty of annotating 3D geometry from monoc...
Modern Text-to-Image (T2I) diffusion models have achieved remarkable semantic alignment, yet they often suffer from a significant lack of variety, converging on...
Accurate 3D understanding of human hands and objects during manipulation remains a significant challenge for egocentric computer vision. Existing hand-object in...
We present FlowIt, a novel architecture for optical flow estimation designed to robustly handle large pixel displacements. At its core, FlowIt leverages a hiera...
Tremendous progress in visual scene generation now turns a single image into an explorable 3D world, yet immersion remains incomplete without sound. We introduc...
Robotic mapping systems typically approach building metric-semantic scene representations from the robot's own sensors and cameras. However, these 'first person...
Vision-language models (VLMs) have shown impressive capabilities across diverse tasks, motivating efforts to leverage these models to supervise robot learning. ...
Flow-GRPO successfully applies reinforcement learning to flow models, but uses uniform credit assignment across all steps. This ignores the temporal structure o...
Long video understanding remains challenging for Multi-modal Large Language Models (MLLMs) due to high memory costs and context-length limits. Prior approaches ...
Facial recognition systems are increasingly deployed in law enforcement and security contexts, where algorithmic decisions can carry significant societal conseq...
Endpoint POST /v1/drawings/detection/doors Detect doors in architectural floor‑plan PDFs. Accepts a previously uploaded document_id, enqueues inference, and re...
Multimodal Large Language Models (MLLMs) achieve stronger visual understanding by scaling input fidelity, yet the resulting visual token growth makes jointly su...
In federated healthcare systems, Federated Class-Incremental Learning (FCIL) has emerged as a key paradigm, enabling continuous adaptive model learning among di...
Over the past few years, we’ve been building a mobile‑first AI skin analysishttps://skinive.com/ system used by +1 000 000 users worldwide except the USA and Ca...
Reconstructing 3D geometry and appearance from a sparse set of fixed cameras is a foundational task with broad applications, yet it remains fundamentally constr...
Most recent advances in 3D generative modeling rely on diffusion or flow-matching formulations. We instead explore a fully autoregressive alternative and introd...
Depth from Defocus (DfD) is the task of estimating a dense metric depth map from a focus stack. Unlike previous works overfitting to a certain dataset, this pap...
Equivariance is a fundamental property in computer vision models, yet strict equivariance is rarely satisfied in real-world data, which can limit a model's perf...
We introduce PerceptionComp, a manually annotated benchmark for complex, long-horizon, perception-centric video reasoning. PerceptionComp is designed so that no...
Traditional Visual Grounding (VG) predominantly relies on textual descriptions to localize objects, a paradigm that inherently struggles with linguistic ambigui...
Empowered by large-scale training, vision-language models (VLMs) achieve strong image and video understanding, yet their ability to perform spatial reasoning in...
High-fidelity 3D reconstruction of vehicle exteriors improves buyer confidence in online automotive marketplaces, but generating these models in cluttered deale...
Mobile devices continuously interact with cellular base stations, generating massive volumes of signaling records that provide broad coverage for understanding ...
Large-scale video diffusion models achieve impressive visual quality, yet often fail to preserve geometric consistency. Prior approaches improve consistency eit...
Existing generative video compression methods use generative models only as post-hoc reconstruction modules atop conventional codecs. We propose Generative Vide...
Existing feed-forward 3D Gaussian Splatting methods predict pixel-aligned primitives, leading to a quadratic growth in primitive count as resolution increases. ...
Multi-shot video generation is crucial for long narrative storytelling, yet current bidirectional architectures suffer from limited interactivity and high laten...
Vision Foundation Models (VFMs) have become the cornerstone of modern computer vision, offering robust representations across a wide array of tasks. While recen...
Reference-to-video (R2V) generation is a controllable video synthesis paradigm that constrains the generation process using both text prompts and reference imag...
