Detect unknown and known objects using image semantics and slots with OpenSlot
Survey of resource-efficient backbones for computer vision for each domain
Survey of video anomaly detection over past 10 years with Abdalla
Survey of depth from monocular image and videos using deep learning with Rajapaksha
Segment scene 2x faster using convolution, RWKV, and multiscale tokens with RWKV-SAM
Get 3D scene and location by encoding geometry and appearance as factors for features with DF-SLAM
Segment scene with semi-supervised learning using monocular depth estimation with DG
Segment objects with only image labels using negative region of interest with FBR
Detect all objects 21.3% better than SAM by expanding prompts for Grounding DINO with DiPEx
Super-resolution image by using semantics to reconstruct details with IG-CFAT
Get 3D scene by preferring walls and floor to be flat, vertical, or horizontal with FAWN
Segment scene fast by change multi-path blocks in training to single-path when infer with RDRNet
Weakly supervised segmentation using extracted semantic features from CLIP with WeCLIP
Segment object in noisy image with SAM by standardize the variation in degraded image with RobustSAM
Segment object in new domain using SAM and making input features domain-agnostic with APSeg
Segment scene using DINO-ViT feature space and predict embedding that preserve semantics with SimSAM
Get 3D scene by removing redundant or inaccurate Gaussians and keeping small Gaussians with TrimGS
Get 3D scene using Gaussian splatting with normal, depth maps, and geometric constraints with PGSR
Get 3D object shape using neural implicit with self-supervision on surface normals with SN-NIR
Get 3D of unknown scene from from one image by extend depth estimation to make 3D shape with Flash3D