depth-estimation

brandpose

+13

Personal project: where shoppers look, estimated from an ordinary security camera and open source AI (YOLO11, Gaze-LLE, Depth Anything V2)

GTR

+11

GTR: Gated Token Recurrence for Efficient Dense Prediction

lightly-train

+10

All-in-one training for vision models (YOLO, ViTs, RT-DETR, DINOv3): pretraining, fine-tuning, distillation.

map-anything

+13

MapAnything: Universal Feed-Forward Metric 3D Reconstruction

iris-3b

+7

Iris-3B: pixel-space generation & general vision learner. A 3B diffusion transformer that generates every pixel directly (no VAE); the same prior, fine-tuned, does monocular depth estimation and 4x image restoration. Paper, weights, training code and demo.

OpenSeeFace

+7

Robust realtime face and facial landmark tracking on CPU with Unity integration

pyslam

+4

pySLAM is a hybrid Python/C++ Visual SLAM pipeline supporting monocular, stereo, and RGB-D cameras. It provides a broad set of modern local and global feature extractors, multiple loop-closure strategies, a volumetric reconstruction module, integrated depth-prediction models, and semantic segmentation capabilities for enhanced scene understanding.

zed-sdk

+3

⚡️The spatial perception framework for rapidly building smart robots and spaces

ZipDepth

+3

[ECCV 2026] Official implementation of "ZipDepth: Bringing Lightweight Zero-Shot Monocular Depth Anywhere, on Any Device". A compact 6.1M-parameter network for zero-shot monocular depth estimation, running in real time from server GPUs to mobile phones via knowledge distillation from foundation models.