Create videos featuring real people with controlled actions and consistent identities.
― 6 min read
Computer Science - Computer Vision and Pattern Recognition
RSSSharpDepth enhances depth perception in images, improving clarity for various applications.
― 5 min read
A smarter method for analyzing tissue samples using whole slide images.
― 4 min read
KANs offer flexibility and adaptability in image recognition tasks.
― 6 min read
DistinctAD offers a new method for generating unique audio descriptions in films.
― 4 min read
A new method improves tile classification in Rummikub through reasoning.
― 6 min read
Combining MRI and ultrasound images enhances brain tumor surgery accuracy.
― 5 min read
RPEE-Heads dataset enhances head detection accuracy in crowded environments.
― 6 min read
New methods improve the quality of 3D models from text prompts.
― 4 min read
A look at hyperspectral imaging and its advancements through active transfer learning.
― 5 min read
We improve machine learning by controlling image difficulty in training data.
― 6 min read
Combining expert knowledge with AI boosts cancer diagnosis accuracy.
― 9 min read
Learn how SmileSplat creates 3D images from just a few pictures.
― 9 min read
GLS offers better 3D modeling for indoor spaces, tackling complex scenes effectively.
― 5 min read
New methods improve image transmission for underwater vehicles.
― 7 min read
Using images to help computers grasp word meanings more effectively.
― 6 min read
Learn how mixed precision quantization speeds up image creation.
― 5 min read
New methods enhance how we find images from text descriptions.
― 5 min read
Event cameras redefine motion tracking, improving accuracy and speed.
― 7 min read
A new combination of images and patient stories improves skin disease detection accuracy.
― 7 min read
Easily generate high-quality videos with just a few words using Open-Sora Plan.
― 6 min read
BiPO transforms text into lifelike human dance movements.
― 7 min read
BRRP helps robots understand scenes better with limited information.
― 8 min read
SISeg improves speed and accuracy in medical image analysis.
― 7 min read
AOPath improves how computers answer questions about videos using actions and objects.
― 6 min read
Muon Space launches satellites to measure soil moisture for better agriculture and climate insights.
― 7 min read
Learn how new tech transforms images into immersive sound experiences.
― 7 min read
A new way to animate sketches using just text prompts.
― 6 min read
New methods analyze lung motion to improve cancer treatment planning.
― 6 min read
Learn how scientists identify harmful gases in the air using advanced imaging methods.
― 6 min read
New method pairs CLIP and DINO to classify images without labels.
― 6 min read
Discover how diffusion models are transforming image and video generation.
― 6 min read
A new method unites DINO and CLIP for effective image segmentation using natural language.
― 9 min read
GEOBench-VLM evaluates models for interpreting geospatial data and images.
― 6 min read
Learn how trajectory attention advances camera control for smoother videos.
― 7 min read
FreqFit enhances image recognition by focusing on high-frequency features efficiently.
― 8 min read
Discover how Face2QR personalizes QR codes with style and functionality.
― 6 min read
Transform static 3D models into lively animations with text commands.
― 6 min read
Machines are taking a lead in spotting product defects for better quality.
― 6 min read
A new method improves face recognition across different image conditions.
― 6 min read