Segment unknown objects by training on independent image-mask and image-text pairs with Uni-OVSeg
Get 3D scene using a 3D object surface field with H2O-SDF
Get 3D object shape by aligning grids with the object surface normal with Gaur
Fix motion blur efficiently by sampling more in more blurred areas with Suin
Get 3D scene using geometric context to constrain depth and normal estimates with ASNDepth
Segment 3D scene with unknown objects using NeRF and ranking with CLIP foundation model OV-NeRF
Get 3D scene by using multivariate Gaussian to compute features with MoD-SLAM
Get 3D object shape with the signed distance field (SDF) encoded by a tensor with TensoSDF
Restore image by preventing local and global connections from spreading noise with LIR
Get 3D object shape from ImageNet images by using StyleGAN2 generator with Shen
Vision Mamba more accurate than transformers and is 2.8x faster and uses 86.8% less GPU memory
Real-time unknown object detection using pre-training on large-scale datasets with YOLO-World
Object pose using coordinates from positional encoding with high-frequency components with Park
Get 3D scene and new views using self-supervision for view-independent color component with Du-NeRF
Segment objects in scene using deformable attention location over time with Truong
Restore image using generative prior, model scaling up, and prompts with SUPIR
Get 3D scene by using external and internal geometric priors with PSDF
Segment object into parts unsupervised using knowledge inside stable diffusion using with EmerDiff
Enhance dim images by encoding image features by width, height, and channel with MixNet
Real-time video segmentation using shared decoder with RAP-SAM