Alternatives and similar repositories for GST

Users that are interested in GST are comparing it to the libraries listed below

• SunYangtian / UniGeo
  UniGeo: Taming Video Diffusion for Unified Consistent Geometry Estimation
  ☆132Updated 4 months ago
• nopQAQ / Test3R
  ☆111Updated 4 months ago
• SooLab / MVTokenFlow
  [ICLR 2025] MVTokenFlow: High-quality 4D Content Generation using Multiview Token Flow
  ☆23Updated 6 months ago
• fudan-zvg / UniUGG
  UniUGG: Unified 3D Understanding and Generation via Geometric-Semantic Encoding
  ☆54Updated 2 months ago
• Zerg-Overmind / Can3Tok
  Official code for the paper: Can3Tok (ICCV2025)
  ☆38Updated 2 months ago
• WU-CVGL / SIU3R
  [NeurIPS 2025 Spotlight] Official implementation of the SIU3R: Simultaneous Scene Understanding and 3D Reconstruction Beyond Feature Alig…
  ☆118Updated last month
• Gen-Verse / WideRange4D
  WideRange4D: Enabling High-Quality 4D Reconstruction with Wide-Range Movements and Scenes
  ☆102Updated 7 months ago
• Nut-World / NutWorld
  Seeing World Dynamics in a Nutshell
  ☆109Updated 7 months ago
• ForeverFancy / GVFDiffusion
  [ICCV 2025] Gaussian Variation Field Diffusion for High-fidelity Video-to-4D Synthesis
  ☆93Updated 2 months ago
• vsitzmann / xfactor-nvs
  Public code for XFactor: Introduces the first geometry-free model to achieve true self-supervised / pose-free Novel View Synthesis (NVS) …
  ☆22Updated this week
• sap3d / sap3d
  [CVPR 2024 Hightlight] Code release for "The More You See in 2D, the More You Perceive in 3D"
  ☆64Updated last year
• DSL-Lab / StreamSplat
  StreamSplat: Towards Online Dynamic 3D Reconstruction from Uncalibrated Video Streams
  ☆65Updated 4 months ago
• mohammadasim98 / mv-ldm
  An open source Multi-View Latent Diffusion Model
  ☆38Updated 5 months ago
• VITA-Group / Comp4D
  "Comp4D: Compositional 4D Scene Generation", Dejia Xu*, Hanwen Liang*, Neel P. Bhatt, Hezhen Hu, Hanxue Liang, Konstantinos N. Platanioti…
  ☆77Updated last year
• MegaScenes / nvs
  ☆102Updated last year
• kaist-cvml / 3d-vlm-gd
  [EMNLP 2025 Findings] 3D-Aware Vision-Language Models Fine-Tuning with Geometric Distillation
  ☆24Updated 4 months ago
• YkiWu / Point3R
  [NeurIPS 2025] Streaming 3D Reconstruction with Explicit Spatial Pointer Memory
  ☆152Updated last month
• cwchenwang / physctrl
  [NeurIPS 2025] PhysCtrl: Generative Physics for Controllable and Physics-Grounded Video Generation
  ☆49Updated this week
• ZGCTroy / RealCam-Vid
  open-sourced video dataset with dynamic scenes and camera movements annotation
  ☆76Updated 6 months ago
• wkbian / GS-DiT
  Source code for paper GS-DiT: Advancing Video Generation with Pseudo 4D Gaussian Fields through Efficient Dense 3D Point Tracking
  ☆56Updated 9 months ago
• Mars-tin / 4D-LRM
  Self-reimplemented version of 4D-LRM.
  ☆59Updated 4 months ago
• qq456cvb / 3DCorrEnhance
  ☆35Updated 5 months ago
• HavenFeng / St4RTrack
  Official Implementation of paper "St4RTrack: Simultaneous 4D Reconstruction and Tracking in the World"
  ☆71Updated last month
• mohammadasim98 / met3r
  MEt3R: Measuring Multi-View Consistency in Generated Images
  ☆138Updated 3 months ago
• ueoo / FluidNexus
  [CVPR 2025 Oral] FluidNexus: 3D Fluid Reconstruction and Prediction from a Single Video
  ☆50Updated last month
• ruili3 / lari
  [arXiv'25]🌈 Unseen 3D Geometry Reasoning from a Single Image.
  ☆70Updated 3 months ago
• Stable-X / StableRecon
  StableRecon: Making Video to 3D easy
  ☆76Updated last year
• Dwawayu / Pensieve
  The official implementation for "Recollection from Pensieve: Novel View Synthesis via Learning from Uncalibrated Videos".
  ☆48Updated 5 months ago
• POSTECH-CVLab / RoDyGS
  An official implementation of RoDyGS: Robust Dynamic Gaussian Splatting for Casual Videos
  ☆34Updated 10 months ago
• ByteDance-Seed / TraceAnything
  Trace Anything: Representing Any Video in 4D via Trajectory Fields
  ☆296Updated last week