Open3D v0.20 brings Gaussian Splatting to the Open3D renderer, makes Intel GPU workflows substantially more practical through expanded SYCL Tensor pipelines, and improves the developer experience with smaller installs, Python type checking, and new distribution options.
Note
- Now available.:
open3d-cpuPython 3.11-3.14 wheels are not available in PyPI at the moment due to storage limits. We expect this to be resolved in a few days. - Signed Windows and macOS viewers will be available shortly.
Highlights
Gaussian Splatting
https://github.com/user-attachments/assets/f2840a2a-ffea-4347-9039-e1ecfd089fb2
Gaussian splats and meshes in one Open3D scene.
python examples/python/visualization/draw_from_csv.py
Open3D can now render 3D Gaussian Splats in interactive and offscreen views, along with regular PBR meshes. Load tensor point clouds from Gaussian PLY, binary SPLAT, or compressed SPZ files, then compose them with triangle meshes using correct depth occlusion. This enables applications to combine radiance-field captures with conventional 3D assets in the same Open3D scene (PRs #7191, #7194, #7490, #7520, and #7525; contributed by @lumurillo, @billamiable, @ssheorey, and @jeevan6996).
The renderer supports anti-aliasing, depth output and offscreen rendering (see OffscreenRenderer). See the Gaussian Splatting tutorial, the mixed-scene Python example, and the C++ example.
Labeling geometry over a compressed SPZ Gaussian Splat.
Intel GPU Pipelines Through SYCL
https://github.com/user-attachments/assets/44f03300-c887-4839-9855-1fbd50e15ac0
Real time RGBD reconstruction with dense SLAM on an Intel B580 GPU
pip install open3d-xpu
cd examples/python/t_reconstruction_system
python dense_slam.py --device SYCL:0 --default_dataset lounge --path_npz lounge_sycl.npz
The SYCL backend now supports substantially more Tensor-based Open3D pipelines on Intel integrated and discrete GPUs. New native-device implementations cover HashMap, nearest-neighbor search, geometry transforms, registration, RGB-D odometry, feature computation, TSDF reconstruction, and raycasting. Hybrid nearest-neighbor search now supports L1 and Linf metrics in addition to L2 (PRs #7114 and #7443; contributed by @ssheorey).
The newly implemented Intel GPU algorithms include:
- Core and geometry: device HashMap; KNN, fixed-radius, and hybrid nearest-neighbor search; Tensor geometry and normal transforms; TriangleMesh normal and area computation; and partial Tensor PointCloud unprojection, normal, and NNS-based operations.
- Registration and odometry: point-to-point, point-to-plane, colored, Doppler, and symmetric ICP; registration evaluation and information matrices; FPFH features and correspondence matching; and point-to-plane, intensity, and hybrid RGB-D odometry.
- Reconstruction and raycasting: VoxelBlockGrid TSDF touch, integration, ray casting, point-clo
Comparison of tunnel reconstructions using point-to-plane ICP (left) and Doppler ICP (right) with measurements collected by an FMCW LiDAR (Image from original Doppler-ICP repo)
See 
