[CVPR 2025 Highlight] Video Depth Anything: Consistent Depth Estimation for Super-Long Videos
- depth-estimation
- video-depth
- monocular-depth-estimation
- transformer
98,836 visible repositories in the index
433–456 of 1,071 · Most stars
[CVPR 2025 Highlight] Video Depth Anything: Consistent Depth Estimation for Super-Long Videos
The repo for "Metric3D: Towards Zero-shot Metric 3D Prediction from A Single Image" and "Metric3Dv2: A Versatile Monocular Geometric Foundation Model..."
A Heterogeneous Benchmark for Information Retrieval. Easy to use, evaluate your models across 15+ diverse IR datasets.
An interactive, terminal-based markdown presenter
Label, clean and enrich text datasets with LLMs.
Let Claude (or any LLM) actually watch a video — scene-aware, deduplicated frames + transcript, from a URL or local file. Runs locally, MIT.
[ICLR 2025] From anything to mesh like human artists. Official impl. of "MeshAnything: Artist-Created Mesh Generation with Autoregressive Transformers"
Deep learning PyTorch library for time series forecasting, classification, and anomaly detection (originally for flood forecasting).
The repository host gives no description.
Python m3u8 Parser for HTTP Live Streaming (HLS) Transmissions
Fast State-of-the-Art Static Embeddings
A 0.9B model for long-form transcription in 50+ languages with speaker diarization, timestamps, and acoustic event awareness
A lightweight framework for building LLM-based agents
Unsupervised Word Segmentation for Neural Machine Translation and Text Generation
A self-learning data agent built with systems engineering principles. It grounds answers in 6 layers of context and improves with every query.
Ongoing research training transformer language models at scale, including: BERT & GPT-2
The implementation of DeBERTa
📺 An End-to-End Solution for High-Resolution and Long Video Generation Based on Transformer Diffusion
[CVPR 2025] Official PyTorch Implementation of MambaVision: A Hybrid Mamba-Transformer Vision Backbone
Cutting edge AI technology for automated audio transcription. A nice GUI for OpenAIs Whisper and pyannote (speaker identification)
Official implementation for "iTransformer: Inverted Transformers Are Effective for Time Series Forecasting" (ICLR 2024 Spotlight)
Lumina-T2X is a unified framework for Text to Any Modality Generation
PyPSA: Python for Power System Analysis
The FindMy Flipper app turns your FlipperZero into an AirTag or other tracking device, compatible with Apple AirTags and Samsung SmartTag and Tile Trackers. It uses the BLE beacon to broadcast, allowing users to clone existing tags, generate OpenHaystack key pairs for Apple's FindMy network, and customize beacon intervals and transmit power.