Get 3D scene with fewer images by adapting scene priors trained on large datasets with NFP 3D Reconstruction with Generalizable Neural...

Real-time unsupervised video object segmentation by training with images and optical flow with TMO Treating Motion as Option with Output...

Segment scene in new domain with one image using adversarial refinement with SITTA-SEG Single Image Test-Time Adaptation for Segmentation...

Get 3D object from scene by lifting Segment Anything Model masks into 3D field with NOC NOC: High-Quality Neural Object Cloning with 3D...

Real-time video object segmentation by using global assignment and semantic features with TCOVIS TCOVIS: Temporally Consistent Online...

3D point cloud segmentation with few examples using shared geometric components with GFS-3DSeg_GWs Generalized Few-Shot Point Cloud...

Survey of human gait recognition using deep learning Human Gait Recognition using Deep Learning: A Comprehensive Review arXiv paper...

Get 3D scene by using view-dependent colors and constraints on geometry and photography with Yu Improving Neural Indoor Surface...

Detect object with few examples and hidden parts by extending local to co-existing regions with ECEA ECEA: Extensible Co-Existing...

Get camera position from image and 3D point clouds by match image patch to points with EP2P-Loc EP2P-Loc: End-to-End 3D Point to 2D Pixel...

Get 3D scene using multiple priors and regularizers with Lincetto Exploiting Multiple Priors for Neural 3D Indoor Reconstruction arXiv...

Detect object by train on text-to-image for foreground and background with Text2Image-for-Detection Beyond Generation: Harnessing Text to...

Survey of small object detection using transformers Transformers in Small Object Detection: A Benchmark and Survey of State-of-the-Art...

Segment object in video from text description by global information from object queries with TempCD Temporal Collection and Distribution...

Get 3D object shape from one image by synchronizing generated images of many views with SyncDreamer SyncDreamer: Generating...

Complete 3D scene by fusion of depth and color features at different scales with AGG-Net AGG-Net: Attention Guided Gated-convolutional...

Real-time 3D scene reconstruction from monocular, stereo, RGB-D input using all history with GO-SLAM GO-SLAM: Global Optimization for...

Detect unknown objects using unsupervised region proposal methods with MEPU Unsupervised Recognition of Unknown Objects for Open-World...

Get 3D scene from one image by using the distances between points in a latent space with SQLdepth SQLdepth: Generalizable Self-Supervised...

Segment unknown object match text description by generative and discriminative models with Ref-Diff Ref-Diff: Zero-shot Referring Image...