Segment scene with unknown objects without training by diffusion for reference embedding with FreeDA
Video object segmentation using space-time multi-level association with Miao
Get 3D object shape from unposed images by use semantic template feature to estimate pose with TeFF
Deblur image using selective state space model and simplified channel attention with ALGBlock
Get 3D scene from from one image by integrate each reconstruct 3D object into scene with Gen3DSR
Get 3D scene surface from Gaussian splatting by generate new stereo pairs to get depth with gs2mesh
Super-resolution image with unknown degradation using high resolution for refinement with AddSR
Get 3D scene by using signed distance field within 3D Gaussians with 3DGSR
Segment scene with new objects without forgetting old ones using visual prompt tuning with ECLIPSE
Get absolute depth of scene from one image in new domain by seperate camera from depth with UniDepth
Get out-of-distribution objects by observe they fall outside boxes for in-distribution data with BAM
Real-time video object segmentation by encoding frame smoothness and low memory with MAVOS
Get 3D scene using 3D Gaussian splatting with neural signed distance fields with GSDF
Segment scene in new domain by reduce bias when mix source and target domain with Guidance-Training
Get many 3D object shapes from images using segmentation and signed distance with ClusteringSDF
Deblur image using transformers that modulate self-attention outputs dynamically with DeblurDiNAT
Get many 3D object shapes in one image using spatially-aware diffusion guidance with ComboVerse
Get 3D scene from monocular images by distilling the knowledge in stable diffusion with GeoWizard
Survey of synthetic data augmentation in computer vision
Segment images with SAM 30x faster and 3.5% memory using dilated flash attention with SAM-Lightening