Repository for Meta Chameleon, a mixed-modal early-fusion foundation model from FAIR.

[CVPR 2024 Oral] MemSAM: Taming Segment Anything Model for Echocardiography Video Segmentation.

Labeling tool with SAM(segment anything model),supports SAM, sam-hq, MobileSAM EdgeSAM etc.交互式半自动图像标注工具

Official Implementation of CVPR24 highligt paper: Matching Anything by Segmenting Anything

PyTorch code and models for V-JEPA self-supervised learning from video.

[arXiv 2024] DreamScene4D: Dynamic Multi-Object Scene Generation from Monocular Videos

Official repository for "AM-RADIO: Reduce All Domains Into One"

4M: Massively Multimodal Masked Modeling

Code release for "UniVS: Unified and Universal Video Segmentation with Prompts as Queries" (CVPR2024)

[ECCV'2024] Gaussian Grouping for open-world Anything reconstruction, segmentation and editing.

[CVPR 2024 - Oral, Best Paper Award Candidate] Marigold: Repurposing Diffusion-Based Image Generators for Monocular Depth Estimation

Metric depth estimation from a single image

The repo for "Metric3D: Towards Zero-shot Metric 3D Prediction from A Single Image" and "Metric3Dv2: A Versatile Monocular Geometric Foundation Model..."

Curated list of papers and resources focused on 3D Gaussian Splatting, intended to keep pace with the anticipated surge of research in the coming months.

[ICCV 2023] Tracking Anything with Decoupled Video Segmentation

WebGL 3D Gaussian Splat Viewer

[ICCV'23] Cascade-DETR: Delving into High-Quality Universal Object Detection

Original reference implementation of "3D Gaussian Splatting for Real-Time Radiance Field Rendering"

CVPR 2023: Learning to Render Novel Views from Wide-Baseline Stereo Pairs

[ICCV 2023] Code for NeRF-Det: Learning Geometry-Aware Volumetric Representation for Multi-View 3D Object Detection

[ICLR 2023] "Is Attention All NeRF Needs?" by Mukund Varma T*, Peihao Wang* , Xuxi Chen, Tianlong Chen, Subhashini Venugopalan, Zhangyang Wang

A curated list of awesome neural radiance fields papers

PyTorch code and models for the DINOv2 self-supervised learning method.

A curated list of recent diffusion models for video generation, editing, restoration, understanding, etc.

Zero-1-to-3: Zero-shot One Image to 3D Object (ICCV 2023)

[NeurIPS 2023] Official code of "One-2-3-45: Any Single Image to 3D Mesh in 45 Seconds without Per-Shape Optimization"

An open source implementation of CLIP.

[ECCV 2024] Official implementation of the paper "Semantic-SAM: Segment and Recognize Anything at Any Granularity"