Real-time 3D human pose on mobile devices using human model with BlazePose GHUM Holistic BlazePose GHUM Holistic: Real-time 3D Human...

Get distance of far objects by using reference objects with R4D R4D: Utilizing Reference Objects for Long-Range Distance Estimation arXiv...

Unknown object detection by training with phrase and region pairs with GLIP Grounded Language-Image Pre-training arXiv paper abstract...

Predict future depth and motion using only self-supervised raw images as input Forecasting of depth and ego-motion with transformers and...

Improve neural surface reconstruction by modeling high-frequency details with HFS Improved surface reconstruction using high-frequency...

Get 3D mesh of head that is realistic using one image with ROME Realistic One-shot Mesh-based Head Avatars arXiv paper abstract...

Real-time detection of 3D planes in video by merging observations with PlanarRecon PlanarRecon: Real-time 3D Plane Detection and...

Detect 3D shapes of objects and their 3D locations from one image with USL Learning 3D Object Shape and Layout without 3D Supervision...

3D object reconstruction from 2-3 images using geometry reasoning with SparseNeuS SparseNeuS: Fast Generalizable Neural Surface...

Better small object detection by using Wasserstein distance with NWD A Normalized Gaussian Wasserstein Distance for Tiny Object Detection...

Detect image anomalies from many classes using one model with UniAD A Unified Model for Multi-class Anomaly Detection arXiv paper...

Improve monocular 3D depth using fusion of estimated depth over time with PRT-Fusion Depth Estimation Matters Most: Improving Per-Object...

Get better depth from monocular images by using segmentation masks with MaskDepth Layered Depth Refinement with Mask Guidance arXiv paper...

Get improved room layout from image by using pixel meaning with SRW-Net Semantic Room Wireframe Detection from a Single View arXiv paper...

Better image classification in new domain by focusing on foreground with RobustViT Optimizing Relevance Maps of Vision Transformers...

Train 3D segmentation network using simple bounding boxes with Box2Mask Semantic Instance Segmentation of 3D Scenes Through Weak Bounding...

Improve 3D scene reconstruction using monocular depth and normal cues with MonoSDF MonoSDF: Exploring Monocular Geometric Cues for Neural...

Get 3D object from images captured under unknown conditions in the wild with SAMURAI SAMURAI: Shape And Material from Unconstrained...

Adapt visual tasks to new domain without source domain data with DistillAdapt DistillAdapt: Source-Free Active Visual Domain Adaptation...

Better object pose and tracking by propagating keypoints with CenterPoseTrack Keypoint-Based Category-Level Object Pose Tracking from an...