Depth Completion
9개 벤치마크 · 논문 287편 · 이 태스크의 논문 보기 →
Benchmarks
KITTI Depth Completion
VOID
NYU-Depth V2
KITTI
Matterport3D
PLAD
VOID-150
Most implemented
Parse Geometry from a Line: Monocular Depth Estimation with Partial Laser Observation
PENet: Towards Precise and Efficient Image Guided Depth Completion
Indoor Depth Completion with Boundary Consistency and Self-Attention
Noise-Aware Unsupervised Deep Lidar-Stereo Fusion
Papers
RbFT-Net: Rectify-Before-Fuse Temporal Radar Anchors for 4D Radar-Camera Depth Completion
Dense metric depth prediction from cameras and millimeter-wave radar offers a cost-effective sensing solution for autonomous systems. However, radar measurements are inherently sparse and susceptible to clutter, multipat…
Depth CompletionVision Pretraining for Dense Spatial Perception
Dense spatial perception is essential for physical intelligence, where visual systems are expected to recover structured, metric, and actionable representations from pixel observations. Modern visual foundation models te…
Depth CompletionDepth EstimationAISPO: Enhancing Depth Reliability for Robotic Manipulation of Non-Lambertian Objects via Affine-Invariant Shape Prior
Reliable depth perception is critical for robotic manipulation, especially for non-Lambertian objects such as transparent or highly specular surfaces, where raw depth measurements are often corrupted or missing. These fa…
Depth CompletionMotion PlanningShotcreteDepth: A Bi-modal Dataset for Robust Robotic Depth Perception in Shotcrete Construction Environments
We introduce ShotcreteDepth, a bi-modal dataset from the construction domain that captures both an active shotcreting process and general construction environments. The dataset comprises stereo RGB imagery and LiDAR poin…
Depth EstimationDepth CompletionPoint CloudsTrans2Occ: Voxel Occupancy Estimation and Grasp for Transparent Objects from Simulation to Reality
Transparent objects remain challenging for robotic perception due to unreliable depth sensing caused by refraction and reflection. While prior approaches rely on multi-view reconstruction or depth completion, they are of…
Depth CompletionRobotic GraspingTowards Consistent Video Geometry Estimation
This work presents ViGeo, a feed-forward foundation model for recovering spatially dense and temporally consistent geometry from video sequences. Built upon a plain transformer architecture without task-specific architec…
Depth EstimationDepth Completion