ONNX-Unidepth-Monocular-Metric-Depth-Estimation
Python scripts performing Metric Monocular Depth Estimation using the Unidepth model in ONNX.
- 97
- Python
- MIT
- 2 y ago
Python scripts performing Metric Monocular Depth Estimation using the Unidepth model in ONNX.
Experimental demonstration for the Qwen/Qwen-Image-Edit-2511 model with lazy-loaded LoRA adapters supporting multi-image input editing. Users can upload one or more images (gallery format) and apply advanced edits such as pose transfer, anime conversion, or camera angle changes via natural language prompts. Features integrated Rerun SDK.
REFLEX Dataset: A Multimodal Dataset of Human Reactions to Robot Failures and Explanations
TRELLIS.2-Text-to-3D-FA2 is an advanced, experimental 3D asset generation suite that couples high-speed text-to-image synthesis with structured 3D geometry reasoning. By linking Alibaba's rapid Tongyi-MAI/Z-Image-Turbo pipeline with Microsoft's state-of-the-art microsoft/TRELLIS.2-4B foundational 3D asset mode.
Idol-Imagine-Fast is a dual-pipeline Text-to-3D and Image-to-3D generation studio that converts single text prompts or reference photographs into high-density 3D Gaussian splats (.ply).
Image-to-3D-Video-Asset-Generator is an all-in-one generative 3D pipeline that transitions smoothly from textual concepts or reference images into fully realized 3D mesh assets (.glb), dynamic camera movements in 5-second MP4 videos, and clean bundle exports (.zip).
A Gradio app with Rerun visualization for Microsoft's TRELLIS.2-4B model that generates textured 3D assets (GLB) from text or images using a two-stage pipeline: text-to-image (Z-Image-Turbo) then image-to-3D (TRELLIS.2).
Experimental demonstration for the Qwen/Qwen-Image-Edit-2511 model with lazy-loaded LoRA adapters for single-image editing tasks. Features specialized edits like photo-to-anime conversion and multi-angle transformations. Unique integration with Rerun SDK: outputs are visualized in an interactive viewer.
HY-World-2.0-Demo is a powerful, experimental 3D reconstruction and Gaussian Splatting suite powered by the Tencent HY-World-2.0 model (WorldMirror).
Upload multiple images or video files, which are then processed to generate high-fidelity 3D reconstructions, accurate depth maps, and normal maps.
Intelligent ADAS development using ROS 2, CARLA, computer vision, object detection, tracking, planning and vehicle simulation.
End-to-end Rerun stack for reBot B601-DM (record â curate â LeRobot v3 â replay)