# Interesting papers ## CAT4D: Create Anything in 4D with Multi-View Video Diffusion Models - https://arxiv.org/pdf/2411.18613 - https://cat-4d.github.io/ - 4D scene generation, multi-view video diffusion model, deformable 3D Gaussian  ## pixelSplat: 3D Gaussian Splats from Image Pairs for Scalable Generalizable 3D Reconstruction - https://openaccess.thecvf.com//content/CVPR2024/papers/Charatan_pixelSplat_3D_Gaussian_Splats_from_Image_Pairs_for_Scalable_Generalizable_CVPR_2024_paper.pdf - https://davidcharatan.com/pixelsplat/  ## LiveScene: Language Embedding Interactive Radiance Fields for Physical Scene Rendering and Control - https://openreview.net/pdf/db46ca38beed8e31670315500fdc6d0bf0bf5757.pdf  ## Talking to DINO: Bridging Self-Supervised Vision Backbones with Language for Open-Vocabulary Segmentation - https://arxiv.org/pdf/2411.19331 - https://lorebianchi98.github.io/Talk2DINO/  ## Navigation World Models - https://www.amirbar.net/nwm/index.html  ## MV-DUSt3R+: Single-Stage Scene Reconstruction from Sparse Views In 2 Seconds - https://arxiv.org/pdf/2412.06974 - https://mv-dust3rp.github.io/ <img width="729" alt="image" src="https://github.com/user-attachments/assets/36af61f1-9d32-4d4e-aa5a-e9cd0c22e419" /> ## MASt3R-SLAM: Real-Time Dense SLAM with 3D Reconstruction Priors - https://edexheim.github.io/mast3r-slam/mast3r-slam.pdf - https://edexheim.github.io/mast3r-slam/   ## Diorama: Unleashing Zero-shot Single-view 3D Scene Modeling - https://arxiv.org/pdf/2411.19492 - https://3dlg-hcvc.github.io/diorama/ <img width="672" alt="image" src="https://github.com/user-attachments/assets/598d316f-2862-4ba6-9999-b6bda1232527" />  ## MegaSaM: Accurate, Fast, and Robust Structure and Motion from Casual Dynamic Videos - https://arxiv.org/pdf/2412.04463 - https://mega-sam.github.io/ - deep visual SLAM framework - Check out website for better examples 
