Real-time object segmentation for videos and images with open-source code and expansive datasets.
SAM 2 provides real-time, promptable object segmentation for both videos and images,...
OpenAI's latest feature makes ChatGPT sound remarkably lifelike, rolling out to paid users starting Tuesday.
ChatGPT's advanced voice mode mimics natural conversation with real-time responses...
Advancing 3D Content Creation through a Generation-Reconstruction Cycle
Cycle3D combines 2D diffusion-based generation with 3D reconstruction for superior image-to-3D conversion.
The framework enhances the quality and...
Advancing Realistic Human Insertion in Diverse Backgrounds
Text2Place generates realistic human placements in various scenes using text guidance.
The method utilizes semantic masks and subject-conditioned inpainting...
Advancing 3D Scene Generation with Holistic Text-to-Image Models
HoloDreamer generates highly consistent 3D panoramic scenes from text descriptions.
The framework combines multiple diffusion models with 3D...
AI Systems Compete at the International Mathematical Olympiad
Google DeepMind’s AI systems solved four out of six problems at this year’s International Mathematical Olympiad.
AlphaProof and...
Solving Object Repetition in High-Resolution Image Generation
AccDiffusion addresses the issue of object repetition in patch-wise higher-resolution image generation.
The method uses patch-content-aware prompts and dilated...
Innovating Object Addition in Images with Text Guidance Alone
Diffree enables seamless text-guided object addition without compromising background consistency.
The model leverages the OABench dataset, enhancing...
Tailoring AI-Generated Images to Individual Tastes
ViPer personalizes image generation by capturing and applying individual visual preferences.
The system uses user comments to infer visual likes...
A New Benchmark for Realistic Human Image Animation and Camera Control
HumanVid introduces the first large-scale, high-quality dataset tailored for human image animation, combining real-world...
Kuaishou's AI Video Generator Goes Global, Challenging OpenAI's Sora
Kling AI, Kuaishou's AI video generator, is now available globally, providing text-to-video and image-plus-text-to-video generation.
Users receive...
NVIDIA's Latest Offering Enhances Data Retrieval for AI Application
NVIDIA introduces NeMo Retriever NIM inference microservices to improve AI accuracy and efficiency.
The microservices are integrated...
