About This repository is a curated collection of the most exciting and influential CVPR 2025 papers. π₯ [Paper + Code + Demo]
β851Jun 16, 2025Updated 8 months ago
Alternatives and similar repositories for top-cvpr-2025-papers
Users that are interested in top-cvpr-2025-papers are comparing it to the libraries listed below
Sorting:
- This repository is a curated collection of the most exciting and influential CVPR 2024 papers. π₯ [Paper + Code + Demo]β742Jun 2, 2025Updated 9 months ago
- Scaling Vision Pre-Training to 4K Resolutionβ221Jan 4, 2026Updated 2 months ago
- [NeurIPS DB 2025] IR3D-Bench: Evaluating Vision-Language Model Scene Understanding as Agentic Inverse Renderingβ45Oct 15, 2025Updated 4 months ago
- β54Feb 27, 2026Updated last week
- Trackers gives you clean, modular re-implementations of leading multi-object tracking algorithms released under the permissive Apache 2.0β¦β2,932Updated this week
- This series will take you on a journey from the fundamentals of NLP and Computer Vision to the cutting edge of Vision-Language Models.β1,157Jan 23, 2025Updated last year
- MambaGlue: Fast and Robust Local Feature Matching With Mamba @ ICRA'25β268Mar 13, 2025Updated 11 months ago
- streamline the fine-tuning process for multimodal models: PaliGemma 2, Florence-2, and Qwen2.5-VLβ2,660Mar 2, 2026Updated last week
- Gaze-LLE: Gaze Target Estimation via Large-Scale Learned Encoders (CVPR 2025, Highlight)β824Apr 19, 2025Updated 10 months ago
- πA curated list of DUSt3R-related papers and resources, tracking recent advancements using this geometric foundation model.β788Nov 5, 2025Updated 4 months ago
- [CVPR 2025 Highlight] Official repository for the paper: "SAMWISE: Infusing Wisdom in SAM2 for Text-Driven Video Segmentation"β367Sep 25, 2025Updated 5 months ago
- β99Mar 31, 2025Updated 11 months ago
- [ICLR 2026] RF-DETR is a real-time object detection and segmentation model architecture developed by Roboflow, SOTA on COCO, designed forβ¦β5,803Updated this week
- The ESMStereo models are designed with low computational complexity to achieve an acceptable balance between accuracy and speed, which maβ¦β57Aug 31, 2025Updated 6 months ago
- A minimal implementation of LLaVA-style VLM with interleaved image & text & video processing ability.β98Dec 17, 2024Updated last year
- [CVPR 2025] Official PyTorch implementation of "EdgeTAM: On-Device Track Anything Model"β881Jan 27, 2026Updated last month
- Pruned CoTracker architecture for tracking the myocardium in 2D echo images.β19May 6, 2025Updated 10 months ago
- Real-time webcam demo with SmolVLM(mlx-community/SmolVLM-Instruct-4bit) and MLX-VLMβ25Jun 12, 2025Updated 8 months ago
- Implementation of "FE-DeTr: Keypoint Detection and Tracking in Low-quality Image Frames with Events". ICRA 2024.β18Dec 19, 2024Updated last year
- [MICCAI 2025] FEATοΌFull-Dimensional Efficient Attention Transformer for Medical Video Generation.β22Sep 24, 2025Updated 5 months ago
- State-of-the-art Image & Video CLIP, Multimodal Large Language Models, and More!β2,181Feb 11, 2026Updated 3 weeks ago
- Official Implementation of CVPR24 highlight paper: Matching Anything by Segmenting Anythingβ1,365May 1, 2025Updated 10 months ago
- MP-SfM: Monocular Surface Priors for Robust Structure-from-Motion (CVPR 2025)β484Jul 9, 2025Updated 8 months ago
- β26Oct 15, 2024Updated last year
- SOTA Spherical Target-based Calibration (accepted in IROS'25)β29Feb 2, 2026Updated last month
- CLaMR: Contextualized Late-Interaction for Multimodal Content Retrievalβ23Jun 28, 2025Updated 8 months ago
- Official Implementation of paper "MonST3R: A Simple Approach for Estimating Geometry in the Presence of Motion"β1,337Jun 16, 2025Updated 8 months ago
- [ICCV 2025] Implementation for Describe Anything: Detailed Localized Image and Video Captioningβ1,456Jun 26, 2025Updated 8 months ago
- Code for the project "MegaSaM: Accurate, Fast and Robust Structure and Motion from Casual Dynamic Videos"β1,240Jan 5, 2026Updated 2 months ago
- The repository provides code for running inference with the Meta Segment Anything Model 2 (SAM 2), links for downloading the trained modeβ¦β18,610Updated this week
- SOTA Distributed LiDAR SLAM (selected spotlight talk in ICRA'25 Workshop on Field Robotics)β116May 14, 2025Updated 9 months ago
- Segment This Thing is an efficient image segmentation models that uses a biologically-inspired foveated tokenization to reduce inference β¦β55Jun 16, 2025Updated 8 months ago
- [ECCV 2024] Decomposition Betters Tracking Everything Everywhereβ112Jul 10, 2024Updated last year
- Official repository for "AM-RADIO: Reduce All Domains Into One"β1,682Feb 11, 2026Updated 3 weeks ago
- UFM: A Unified Dense Image Correspondence Estimator for both Optical Flow & Wide Baseline Matching Tasks. Matches any pair of images. (Neβ¦β299Feb 20, 2026Updated 2 weeks ago
- AllTracker is a model for tracking all pixels in a video.β399Sep 2, 2025Updated 6 months ago
- [RAL 2024 & IROS 2024] Official Implementation of the Plane Extraction Module from "RSS: Robust Stereo SLAM with Novel Extraction and Fulβ¦β19Mar 31, 2025Updated 11 months ago
- DINOv2 module for use with Autodistill.β15Dec 6, 2023Updated 2 years ago
- Collaborative Dynamic 3D Scene Graphs for Open-Vocabulary Urban Scene Understandingβ31Dec 23, 2025Updated 2 months ago