Segment unknown scene with unsupervised learning using UNet diffusion features with DiffCut Zero-Shot Image Segmentation via Recursive...

Get 3D object shape using SDF and generalized multi-scale volume representation with GenS GenS: Generalizable Neural Surface...

Segment scene in new domain using features from diffusion models with DIFF Diffusion Features to Bridge Domain Gap for Semantic...

Get 3D scene using SDF to guide the densify and prune of Gaussians with GaussianRoom GaussianRoom: Improving 3D Gaussian Splatting with...

Segment scene with moving objects and camera by get motion of camera then of object with MCDS-VSS MCDS-VSS: Moving Camera Dynamic Scene...

Segment object even amid similar ones by text-to-image model features without more training with PDM Unveiling the Power of Diffusion...

Detect unknown objects using DINO and SAM to generate object proposals with NIDS-Net Adapting Pre-Trained Vision Models for Novel...

Get 3D shape by representing implicit geometry and radiance fields as points with Chen 3D Reconstruction with Fast Dipole Sums arXiv...

Restore images with many defect types by using shared aspects across diverse degradations with DaAIR Efficient Degradation-aware Any...

Real-time object detector YOLOv10 beats YOLOv9 in speed and size by consistent assignments YOLOv10: Real-Time End-to-End Object Detection...

Get 3D shape using per-pixel intensity renderings rather than estimated normals with NPLMV-PS NPLMV-PS: Neural Point-Light Multi-View...

Get 3D shape and pose of deformable object by first learn coarse parameters and then motion with S3O S3O: A Dual-Phase Approach for...

Survey of 3D point classification and segmentation using deep learning A comprehensive overview of deep learning techniques for 3D point...

Segment images with SAM 48.9x faster by using EfficientViT with EfficientViT-SAM EfficientViT-SAM: Accelerated Segment Anything Model...

Real-time unknown object detection by using only high-level image features with Grounding DINO 1.5 Grounding DINO 1.5: Advance the "Edge"...

Super-resolution image by decomposing the 2D convolution of LKA into 1-D kernels with LCAN Large coordinate kernel attention network for...

Segment object with few examples by generating pseudo-episodes from unlabeled data with IPE Image to Pseudo-Episode: Boosting Few-Shot...

Survey of object pose estimation using deep learning Deep Learning-Based Object Pose Estimation: A Comprehensive Survey arXiv paper...

Fix noisy 3D object mesh by transformers and use local geometric and spatial data with SurfaceFormer Mesh Denoising Transformer arXiv...

Get 3D shape and pose of moving object by moving camera by virtual camera, implicit neural with fmov Free-Moving Object Reconstruction...