Detect object with DETR in a new domain unsupervised by randomly mask features with MTM

Survey of incremental semantic segmentation

Survey of human pose estimation, tracking, and action recognition with deep learning

Get 3D objects and poses in one RGB-D image when trained only with synthetic data with FSD

Get 3D scene from many images with holes fixed by fusion with depth priors with Attentive_DF_Prior

Detect 3D object with many cameras using perspective debiasing Lu

Fix blurry, noisy, and low-resolution images by instructing diffusion model with with AutoDIR

Detect unknown and known objects using CLIP to generate feature embeddings and proposals with He

Get 3D object shape using point modeling and uncertainty estimation with Point-NeuS

Get 3D scene and segmentation from one image without 3D truth using segmentation model with S4C

Get 3D object shape from one image by using reference-guided novel view enhancement with HiFi-123

Object detection and segmentation with a simple transformer using scale-aware attention with SimPLR

Get 3D scene from depth images using uncertainty and curvature to guide sampling and with Sang

Get object pose from one input image and a reference using 3D hypothesis verification with Zhao

Get 3D object shape and new view from one image by geometry constraints with Consistent-1-to-3

Survey of AI-generated images as data for computer vision

Get 3D object shape from sparse views without camera poses by aggregating 2D image feature with LEAP

Segment object with only image labels and paying attention to entire parts of objects with COMNet

Segment scene in new domain using multiple sets of discrepancy features with Feng

Get 3D scene with fewer images by adapting scene priors trained on large datasets with NFP