· ai
[Paper] Unified Primitive Proxies for Structured Shape Completion
Structured shape completion recovers missing geometry as primitives rather than as unstructured points, which enables primitive-based surface reconstruction. In...
-
- · ai
[Paper] Grading Handwritten Engineering Exams with Multimodal Large Language Models
Handwritten STEM exams capture open-ended reasoning and diagrams, but manual grading is slow and difficult to scale. We present an end-to-end workflow for gradi...
- · ai
[Paper] Multi-Level Feature Fusion for Continual Learning in Visual Quality Inspection
Deep neural networks show great potential for automating various visual quality inspection tasks in manufacturing. However, their applicability is limited in mo...
- · ai
[Paper] Detecting Performance Degradation under Data Shift in Pathology Vision-Language Model
Vision-Language Models have demonstrated strong potential in medical image analysis and disease diagnosis. However, after deployment, their performance may dete...
- · ai
[Paper] Efficient Deep Demosaicing with Spatially Downsampled Isotropic Networks
In digital imaging, image demosaicing is a crucial first step which recovers the RGB information from a color filter array (CFA). Oftentimes, deep learning is u...
- · ai
PyTorch vs. TensorFlow: Choosing Your AI Framework for 2026
What is TensorFlow? Developed by Google Brain, TensorFlow is a robust and versatile framework known for its extensive collection of tools, libraries, and resou...
- · ai
Computer Vision Services: Building Intelligent Visual Systems with Oodles
Images and videos contain massive amounts of data—but extracting meaningful insights from them requires advanced AI systems. Computer Vision Serviceshttps://www...
- · ai
[Paper] SpaceTimePilot: Generative Rendering of Dynamic Scenes Across Space and Time
We present SpaceTimePilot, a video diffusion model that disentangles space and time for controllable generative rendering. Given a monocular video, SpaceTimePil...
- · ai
[Paper] GaMO: Geometry-aware Multi-view Diffusion Outpainting for Sparse-View 3D Reconstruction
Recent advances in 3D reconstruction have achieved remarkable progress in high-quality scene capture from dense multi-view imagery, yet struggle when input view...
- · ai
[Paper] Edit3r: Instant 3D Scene Editing from Sparse Unposed Images
We present Edit3r, a feed-forward framework that reconstructs and edits 3D scenes in a single pass from unposed, view-inconsistent, instruction-edited images. U...
- · ai
[Paper] FineTec: Fine-Grained Action Recognition Under Temporal Corruption via Skeleton Decomposition and Sequence Completion
Recognizing fine-grained actions from temporally corrupted skeleton sequences remains a significant challenge, particularly in real-world scenarios where online...
- · ai
[Paper] From Inpainting to Editing: A Self-Bootstrapping Framework for Context-Rich Visual Dubbing
Audio-driven visual dubbing aims to synchronize a video's lip movements with new speech, but is fundamentally challenged by the lack of ideal training data: pai...