Segment untrained objects by grouping visual features and enhancing descriptions with O3S
Get pose of many symmetric objects from images using view fusion and symmetry objective with SyMFM6D
Segment object in video from text description using inter-frame and vision-language with IFIRVOS
Get 3D scene from 2D images using signed distance and geometrical constraints with Guo
Get 3D object shape from one image in 45 seconds by 2D diffusion and neural surface with One-2-3-45
Survey of open vocabulary learning to recognize categories beyond the label space
Get 3D scene using the input with context awareness with Symphonies
Survey of semi-supervised object detection
Segment untrained objects from text descriptions using CLIP-based image embeddings with OpenMask3D
Get 3D scene and segmentation using multi-step probability with VPDD
Segment untrained objects from text descriptions using text-to-image diffusion with Peekaboo
Get 3D shape of object with missing points using text-to-image model with SDS-Complete
Get 3D shape of object by combining neural reconstruction and multiple views with C2F2NeUS
Survey of deep learning for image super-resolution with high magnification and unknown distortion
Get 3D scene from one RGB image when trained on RGBD images using with D2-DRDF
Get object pose from only a few images and using an arbitrary object detector with Cas6D
Get 3D scene using neural radiance fields from sparse and noisy poses with SPARF
Enhance dark images quickly by estimating a global curve and using a lookup table with LUT-GCE
Survey of 3D computer vision using point clouds
Survey of transformers for 2D object detection