Popular GitHub Repositories for Cvpr2025

[CVPR 2025] MASt3R-SLAM: Real-Time Dense SLAM with 3D Reconstruction Priors

Official code for the CVPR 2025 paper "SemanticDraw: Towards Real-Time Interactive Content Creation from Image Diffusion Models."

[CVPR'25] RLAIF-V: Open-Source AI Feedback Leads to Super GPT-4V Trustworthiness

Closed-Loop Supervised Fine-Tuning of Tokenized Traffic Models. CVPR 2025.

[CVPR 2025] CityWalker: Learning Embodied Urban Navigation from Web-Scale Videos

[CVPR 2025] Uni4D: Unifying Visual Foundation Models for 4D Modeling from a Single Video

[CVPR 2025] UniGoal: Towards Universal Zero-shot Goal-oriented Navigation

[CVPR 2025 ?]A Large Multimodal Model for Pixel-Level Visual Grounding in Videos

[CVPR 2025] h-Edit: Effective and Flexible Diffusion-Based Editing via Doob’s h-Transform

[CVPR'25] Lessons Learned from a Unifying Empirical Study of Parameter-Efficient Fine-Tuning (PEFT) in Visual Recognition

[CVPR 2025] Tra-MoE: Learning Trajectory Prediction Model from Multiple Domains for Adaptive Policy Conditioning

SplineGS: Robust Motion-Adaptive Spline for Real-Time Dynamic 3D Gaussians from Monocular Video (CVPR 2025)

[CVPR 2025] PyTorch implementation of Diff-II

Official Code for "Continuous and Locomotive Crowd Behavior Generation (CVPR 2025)"

Z-SASLM is a zero-shot framework for multi-style image synthesis that leverages Spherical Linear Interpolation (SLI) to achieve smooth, coherent blending—without any fine-tuning. Accepted at the CVPR 2025 Workshop on AI for Creative Visual Content Generation, Editing and Understanding.