Segment objects by expanding high-quality regions with CorrMatch

Detect new objects by using a model to automatically give more annotations with RAM

Get 3D shape of object by neural reconstruction by derivatives and coarse-to-fine with Neuralangelo

Reconstruct room and polygonal scenes using guided diffusion with PolyDiffuse

Indoor 3D scene reconstruction using a sparse 3D diffusion network with DiffRoom

Segment new object classes using predictions from related old classes with RaSP

Get 3D shape of object by neural reconstruction that models photon-particle interaction with ReTR

Complete point clouds using prior knowledge and causal inference with Point-PC

Get 3D shape of object having real-time rendering using neural volume and texture with NeuManifold

Survey of video human action recognition using deep neural networks

Survey of self-supervised learning for point cloud data

Survey of self-supervised learning using images for generative and discriminative training

Indoor 3D scene reconstruction 10x faster learn and 100x faster render using sparse voxels with Dong

Survey of YOLO from YOLOV1 to YOLOv8 and YOLO-NAS

Survey of question answering on images

Survey of vision transformers and hybrid CNN-transformer variants

Deblur, super-resolution, and inpainting using an efficient diffusion model with DiffPIR

Segment objects by learning a stable hardness value for pixels with Hardness-Level-Learning

Get 3D shape of object by neural reconstruction using bundle of rays with BundleRecon

Unsupervised 3D point cloud segmentation using multicut graph algorithm on features with FreePoint