boxuLibrary
Follow
Stars
We propose Vid-LLM for versatile 3D scene understanding. The framework does not rely on dense 3D inputs or prior poses, making it practical for real-world deployment.
[CVPR 2025 Best Paper Award] VGGT: Visual Geometry Grounded Transformer
Video-Inpaint-Anything: This is the inference code for our paper CoCoCo: Improving Text-Guided Video Inpainting for Better Consistency, Controllability and Compatibility.
Stereo-LiDAR Depth Estimation with Deformable Propagation and Learned Disparity-Depth Conversion (ICRA2024)
LetsGo: Large-Scale Garage Modeling and Rendering via LiDAR-Assisted Gaussian(Published in SIGGRAPH Asia 2024)
add more control to fooocus
[ICCV 2025] VistaDream: Sampling multiview consistent images for single-view scene reconstruction
PyTorch implementation of the ICCV paper "3D-aware Image Generation using 2D Diffusion Models"
[NeurIPS 2024 Best Paper Award][GPT beats diffusion🔥] [scaling laws in visual generation📈] Official impl. of "Visual Autoregressive Modeling: Scalable Image Generation via Next-Scale Prediction". A…
Learning to Reconstruct 3D Manhattan Wireframes from a Single Image
The official source code for "X-Ray: A Sequential 3D Representation for Generation".
[CVPR 2023] DiffusioNeRF: Regularizing Neural Radiance Fields with Denoising Diffusion Models
A method used sliding window filter frame work for RTK-Visual-Inertial-Navigation
Original reference implementation of "3D Gaussian Splatting for Real-Time Radiance Field Rendering"
[CVPR 2024 Highlight] Scaffold-GS: Structured 3D Gaussians for View-Adaptive Rendering
This is a pipeline to construct HD Semantic Map and HD Vector Map by IPNL.
[ICCV2023] NeRF-LOAM: Neural Implicit Representation for Large-Scale Incremental LiDAR Odometry and Mapping
PLVS is a real-time SLAM system with points, lines, volumetric mapping and 3D unsupervised incremental segmentation.
[RA-L 2022] Ctrl-VIO: Continuous-Time Visual-Inertial Odometry for Rolling Shutter Cameras
Official Implementation of our CVPR 2023 paper: "DBARF: Deep Bundle-Adjusting Generalizable Neural Radiance Fields"
comparison of plucker parameter representation and the parameter representation proposed by ours
Let's learn computer literacy together!
ICE-BA-ros, add loopclosure,equi_distort(fisheye) 以及中文注释
A nonlinear least square(NLLS) solver. Fomulate the NLLS as graph optimization.