Humanoid-OmniOcc delivers a large-scale panoramic stereo occupancy dataset for humanoid robots via Real2Sim2Real, with a model that outperforms monocular baselines in both unseen sim scenes and real settings.
Stereo anything: Unifying stereo matching with large-scale mixed data
7 Pith papers cite this work. Polarity classification is still indexing.
7
Pith papers citing it
verdicts
UNVERDICTED 7representative citing papers
A unified dual-shutter framework and dual-stream network jointly correct blur and rolling-shutter distortion to reconstruct high-speed video from real-world degraded image pairs.
PicoEyes delivers a unified end-to-end model for full 3D gaze estimation including eye parameters, axes, segmentation and depth from monocular or binocular near-eye images, supported by a new large-scale multi-view dataset.
StereoFactory merges stereo matching foundation models via genetic subset search followed by CMA-ES module routing, reporting lower average errors on four benchmarks than baselines while using 2.7-3.7% of retraining time.
Lite Any Stereo delivers top-ranked zero-shot accuracy on four real-world stereo benchmarks using a lightweight backbone, hybrid cost aggregation, and three-stage training on million-scale data, at less than 1% of typical computational cost.
LAS2 is a series of efficient stereo matching models that reach state-of-the-art zero-shot performance among fast methods while running 1.8-2.7x faster than prior iterative approaches on H200 and Orin hardware.
ROVR is a new diverse depth dataset for autonomous driving with 200K frames, released pipelines, and ablations showing sparse ground truth supports model training.
citing papers explorer
-
Lite Any Stereo: Efficient Zero-Shot Stereo Matching
Lite Any Stereo delivers top-ranked zero-shot accuracy on four real-world stereo benchmarks using a lightweight backbone, hybrid cost aggregation, and three-stage training on million-scale data, at less than 1% of typical computational cost.
-
ROVR-Open-Dataset: A Large-Scale Depth Dataset for Autonomous Driving
ROVR is a new diverse depth dataset for autonomous driving with 200K frames, released pipelines, and ablations showing sparse ground truth supports model training.