[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,…

[CVPR 2026] UniCorrn: Unified Correspondence Transformer Across 2D and 3D

Cross-Compile Nvidia Jetson Apps on x86_64 Without a real Jetson device

GStreamer plugins for zero-copy NVMM video on NVIDIA Jetson (Xavier, Orin). Allocator, VIC transform, shared-memory IPC.

Code for the Boxer research paper

[CVPR 2026 (Highlight)] Scal3R: Scalable Test-Time Training for Large-Scale 3D Reconstruction

[ECCV 2026] LoMa: Local Feature Matching Revisited

DELTA: Dense Efficient Long-range 3D Tracking for Any video (ICLR 2025)

[CVPR 2026] DAGE: Dual-Stream Architecture for Efficient and Fine-Grained Geometry Estimation

SOMA: Unifying Parametric Human Body Models

Official implementation of ArUco nano, a lightweight implementation of the ArUco marker detection algorithm up to 6.5x faster than standard OpenCV ArUco.

Ranking and Covariances for Practical Learned Keypoints

The official implementation of InfiniteVGGT

[CVPR 2026] Fast-FoundationStereo: Real-Time Zero-Shot Stereo Matching

Official implementation of "Lotus-2: Advancing Geometric Dense Prediction with Powerful Image Generative Model"

Official implementation of "MV-TAP: Tracking Any Point in Multi-View Videos"

The repository provides code for running inference with the SAM 3D Body Model (3DB), links for downloading the trained model checkpoints and datasets, and example notebooks that show how to use the…

The repository provides code for running inference and finetuning with the Meta Segment Anything Model 3 (SAM 3), links for downloading the trained model checkpoints, and example notebooks that sho…

SAM 3D Objects

Official implementation of "S²M²: Scalable Stereo Matching Model for Reliable Depth Estimation, ICCV 2025"

[ICLR'26] IGGT: Instance-Grounded Geometry Transformer for Semantic 3D Reconstruction

Wrapper of 50+ image matching models with a unified interface

[ICLR 2026] A simple state update rule to enhance length generalization for CUT3R

HISDF (Human Instance, Skeleton, and Depth Fusion) is a unified model that fuses human instance segmentation, skeletal structure estimation, and depth prediction to achieve holistic human perceptio…

[NeurIPS 2025] Pixel-Perfect Depth

VGGT-X: When VGGT Meets Dense Novel View Synthesis

[CVPR'25 Oral] MoGe: Unlocking Accurate Monocular Geometry Estimation for Open-Domain Images with Optimal Training Supervision

Reference PyTorch implementation and models for DINOv3

[CORL 2025 Oral]One View, Many Worlds: Single-Image to 3D Object Meets Generative Domain Randomization for One-Shot 6D Pose Estimation.