Get absolute depth of scene from monocular image by diffusion, field-of-view, augmentation with DMD
Get 3D object shape using a prior from fusing multiple local SDF fields with PR-NeuS
Segment 3D object using 2D instance masks from RGB-D frames with Open3DIS
Real-time super-resolution video by propagating the motion field of the previous frame with TMP
Survey of unknown object detection with Barcina-Blanco
Segment unknown objects using VLM to filter texts and enhance masks with CLIP as RNN
Segment 3D scene with only class existence tags by using scene primitives with Densify Your Labels
Segment object with few examples using multi-level prototype generation with Bao
Get 3D object from many views as good as scanner using multi-resolution hash encode with SuperNormal
Segment scene in unknown domains by efficiently fine-tuning Vision Foundation Models with Rein
Segment object with only image labels using CLIP and SAM to make segmentation seeds with Yang
Survey of image classification with vision transformers
Survey of methods for handling distribution shifts for robust computer vision
Get 3D object from monocular RGB-D video using diffusion prior with MorpheuS
Segment areas, objects, and parts in a scene at the same time with JPPF
Segment scene using information from vision-language models without neural training with PnP-OVSS
Segment scene using vision-language models for diverse semantic knowledge with SemiVL
Segment image into open set of categories using cost from a hierarchical encoder with SED
Segment image with one example using model correspondence between example and target with SEGIC
Real-time object pose from one RGB-D image using hierarchical binary surface encoding with HiPose