NVlabs / L4PLinks
(3DV 2026 Oral) L4P -- a feed-forward foundational model designed for multiple low-level 4D vision perception tasks.
☆55Updated last month
Alternatives and similar repositories for L4P
Users that are interested in L4P are comparing it to the libraries listed below
Sorting:
- Official repo for: Epipolar Geometry Improves Video Generation Models☆74Updated 3 months ago
- [ICLR 2025] Where Am I and What Will I See : An Auto-Regressive Model for Spatial Localization and View Prediction☆42Updated 5 months ago
- Official code for paper: "RayRoPE: Projective Ray Positional Encoding for Multi-view Attention"☆34Updated last week
- ☆123Updated 7 months ago
- Official implementation of Video-DPM☆134Updated last week
- StreamSplat: Towards Online Dynamic 3D Reconstruction from Uncalibrated Video Streams☆73Updated 7 months ago
- [ICCV 2025] This is the official implementation of POMATO: Marrying Pointmap Matching with Temporal Motions for Dynamic 3D Reconstruction☆117Updated 5 months ago
- [Arxiv'25] MGVQ: Could VQ-VAE Beat VAE? A Generalizable Tokenizer with Multi-group Quantization☆54Updated 4 months ago
- Official Implementation of paper "St4RTrack: Simultaneous 4D Reconstruction and Tracking in the World"☆106Updated 4 months ago
- UniGeo: Taming Video Diffusion for Unified Consistent Geometry Estimation☆135Updated 7 months ago
- [EMNLP 2025 Findings] 3D-Aware Vision-Language Models Fine-Tuning with Geometric Distillation☆30Updated 7 months ago
- Official implementation of DepthLM☆290Updated this week
- Code for Faster VGGT with Block-Sparse Global Attention☆90Updated 2 months ago
- WideRange4D: Enabling High-Quality 4D Reconstruction with Wide-Range Movements and Scenes☆106Updated 10 months ago
- Any4D: Unified Feed-Forward Metric 4D Reconstruction☆270Updated last month
- EvoWorld: Evolving Panoramic World Generation with Explicit 3D Memory☆59Updated 2 weeks ago
- [NeurIPS 2025] Streaming 3D Reconstruction with Explicit Spatial Pointer Memory☆177Updated 4 months ago
- Gen3R: 3D Scene Generation Meets Feed-Forward Reconstruction☆143Updated 2 weeks ago
- An official implementation of RoDyGS: Robust Dynamic Gaussian Splatting for Casual Videos☆37Updated last year
- The official implementation of InfiniteVGGT☆265Updated last week
- Official implementation of "E3D-Bench: A Benchmark for End-to-End 3D Geometric Foundation Models"☆104Updated 7 months ago
- (CVPR2025 Highlight) Official repository of paper "Panorama Generation From NFoV Image Done Right"☆18Updated 8 months ago
- One4D: Unified 4D Generation and Reconstruction☆78Updated last month
- Seeing World Dynamics in a Nutshell☆111Updated 10 months ago
- ☆278Updated 3 months ago
- Pytorch implementation of GaussianToken: An Effective Image Tokenizer with 2D Gaussian Splatting☆101Updated 9 months ago
- UniUGG: Unified 3D Understanding and Generation via Geometric-Semantic Encoding☆58Updated 5 months ago
- Orient Anything V2, NeurIPS 2025 Spotlight☆190Updated last week
- [CVPR 2025] Uni4D: Unifying Visual Foundation Models for 4D Modeling from a Single Video☆220Updated 8 months ago
- ☆26Updated 10 months ago