Tag: computer-vision
81 results
SHARP 3D
Turn photos into interactive 3D scenes
MONAI
AI toolkit for healthcare imaging
SAM3D
Segment Anything in 3D scenes
InternVL
Open source multimodal model rivaling GPT-4o
VOID
Remove objects and their interactions from video
Isaac ROS Visual SLAM
GPU-accelerated visual SLAM and odometry
MVInverse
Feed-forward multi-view inverse rendering in seconds
FutureSightDrive
Visual spatio-temporal CoT for autonomous driving
DAAAM
Real-time spatio-temporal memory for robots
CityGaussian
Large-scale scene reconstruction with Gaussians
NavDP
Sim-to-real navigation diffusion policy
Depth Any Panoramas
Foundation model for panoramic depth
TTT3R
3D reconstruction as test-time training
Rex-Omni
Detect anything via next point prediction
Spann3R
3D reconstruction with spatial memory
G3Reg
Fast global registration for outdoor LiDAR
A-LOAM
Advanced implementation of LOAM
ReconViaGen
Accurate multi-view 3D reconstruction via generation
SimpleStream
Simple baseline for streaming video understanding
Depth Anything 3
Recovering visual space from any views