Survey of low-light image and video enhancement

Survey of graph neural networks in computer vision with architectures, datasets, common approaches

Survey of Neural Radiance Field in 3D Vision

Improve image segmentation by identifying and relabeling out-of-candidate pixels with OCR

Reconstruct 3D objects using multi-view features and signed ray distance functions with VolRecon

Better object detection with few examples by get characteristics regardless of class with hANMCL

Improve object segmentation in video using instance information with ISVOS

3D scene reconstruction when data sparse by filling in using diffusion with rgbd-diffusion

Better segmentation with semi-supervised learning by augmentation with AugSeg

Continually adapt model to new domains without catastrophic forget using visual prompts with CTAP

Improve depth resolution at any scaling factor using geometric information with GeoDSR

Better object detection by filtering extra unlabeled data with RUPL

Improve human pose estimation using distance and direction of keypoints with Ji

Better object detection when train with image-level labels by using synthetic data with D2DF2WOD

Get 3D object geometry and new views from 2 images by getting consistent scenes with SparseFusion

Improve 3D surface reconstruction from point clouds using geometry in distance function with GeoUDF

Better image segmentation by using image preprocessing network for a model by with ION

Retrieve images having a region similar to what is highlighted in the query with VFS

Reconstruct 3D objects even with open surfaces using unsigned distance functions with NeuralUDF

Monocular 3D depth for edge device with self-supervised learn by CNN and transformers with Lite-Mono