Segment objects with only image labels using pixel and semantic context in training data with DSCNet

Segment objects in videos by generating an auxiliary frame between adjacent frames with Chen

Segment scene with SAM efficiently by change bimodal distribution to quantized normal with PTQ4SAM

Segment moving object with moving camera by deep learning and fusion of geometric models with Huang

Fix motion blur by integrating the high frequency for edge and low frequency for structure with MCMS

Segment object using stable diffusion to fine-tune SAM with ASAM

Get 3D scene using 2D Gaussian surface elements to remove normal ambiguity with Dai

Segment scene with semi-supervised learning by inter-pixel relation in pseudo-labels with IPixMatch

Restore image by learning from one image using efficient patch-based learning with Pereg

Super-resolution image with unknown degradation by iterative kernel and estimate noise with IKR-Net

Get many 3D object shapes using SAM, 3DGS, Stabled Diffusion, and SuGaR with OMEGAS

Survey of multi-view 3D object recognition using deep models

Segment objects in videos using only bounding boxes by predict targets in training set with PM-VIS

Segment 3D object using 3D Gaussian Splatting with segmentation feature vector with Silva

Get 3D object shape using deformable 3D Gaussians and time-consistent mesh with DG-Mesh

Get 3D scene by ray-tracing for volume rendering of 3D Gaussians with GOF

Reconstruct image from several noisy, blurred, dim images by flow and spatial attention with IREANet

Detect unknown objects in hierarchy by making image descriptions for training with DetCLIPv3

Segment scene with unknown objects by enhance localization capabilities of CLIP with NACLIP

Segment scene with unknown objects by transferable sparse models and efficient tuning with OpenTrans