MVSplat (fastforks)
MVSplat (Chen et al. 2024): feed-forward 3D Gaussian splatting and depth from posed, calibrated images. A UniMatch CNN and multi-view swin transformer feed a plane-sweep cost volume (all other views), refined by 2D U-Nets with cross-view attention into every view's depth; a Gaussian head predicts one Gaussian per pixel (opacity, scale, rotation, degree-4 SH) in the given world frame (result.gaussians, .save("scene.ply")). Forward pass only: no renderer.
This repo is the model card only: it holds no weights. fastforks downloads the authors' weights from the links below and checks them against the SHA-256 in the model card. Code: https://github.com/kleinicke/fastforks. Kernels for the kernels backend: https://huggingface.co/fastforks/kernels. Original code: https://github.com/donydchen/mvsplat at 01f9a28.
Task: multiview. Tier: experimental. Outputs: depth, confidence, gaussians. Backends: portable, kernels.
Input: several images of one scene (posed and calibrated for multi-view stereo, unposed otherwise). Output: depth maps and, where the model predicts them, cameras and 3-D points.
Variants
Weights are the authors' files (not hosted here). SHA-256 shortened to 12 hex digits; the full hashes are in card.toml.
| variant | weights (author link) | SHA-256 | weights licence | commercial use |
|---|---|---|---|---|
mvsplat-re10k@1 |
re10k.ckpt | 83d0d9eaa753 |
MIT | yes |
Licence
Original-code strings, recorded as they are (research-use package; check them before any other use). Code: MIT. Licence files: LICENSE.
Training data: RealEstate10K (camera trajectories of YouTube real-estate videos) (RealEstate10K (YouTube videos, camera poses from ORB-SLAM; research use per its release), the backbone initialised from UniMatch (GMDepth, ScanNet).).
- Licence note: Only the RealEstate10K checkpoint is shipped (MIT code and weights); the ACID checkpoint has the same architecture.
Licence evidence: https://github.com/donydchen/mvsplat/blob/01f9a28edb5eb68416e7e63b01f8d90c3bdfbf01/LICENSE and https://github.com/donydchen/mvsplat/blob/01f9a28edb5eb68416e7e63b01f8d90c3bdfbf01/README.md and https://drive.google.com/drive/folders/14_E_5R6ojOWnLSrSVLVEMHnTiKsfddjU
Input size
any H x W >= 1, resized or padded inside the model
Tested up to (portable, fp16, RTX 5060 Ti 16 GB): mvsplat-re10k 3000x4000 (3.2 GiB peak allocated, 4.4 reserved)
Speed and memory
Multiview, synthetic
| model | input | time (ms): original fp32 | original | portable | kernels | kernels speed-up: vs original | vs portable | peak memory (MiB, allocated / reserved): original | portable | kernels |
|---|---|---|---|---|---|---|---|---|---|---|
mvsplat-re10k |
336x518 | β | 279 | 181 | 172 | 1.6x | 1.0x | 2889 / 4160 | 1239 / 1532 | 1239 / 1532 |
Startup and first call
| model | load (s): original | portable | kernels | first call (s): original | portable | kernels |
|---|---|---|---|---|---|---|
mvsplat-re10k |
1.37 (336x518) | 0.15 (336x518) | 1.27 (336x518) | 2.82 (336x518) | 1.02 (336x518) | 0.69 (336x518) |
torch.compile and TensorRT
| model | input | time: portable | compile | TensorRT fp16 | kernels | preparation: compile (cold first call) | ONNX + engine build | peak MiB (alloc / reserved): portable | compile | kernels | TensorRT (engine + torch) |
|---|---|---|---|---|---|---|---|---|---|---|---|
mvsplat-re10k |
336x518 | 181 ms | 115 ms | planned for 0.2.1 | 172 ms | 102 s | β | 1239 / 1532 | 2762 / 2810 | 1239 / 1532 | β |
Fixed-size cells: time (ms) / peak allocated / peak reserved memory (MiB).
Hardware, protocol and caveats: benchmarks (RTX 5060 Ti 16 GB, sm_120). Original = the original code named above at the precision of portable (fp16, or (fp32) where fp16 is unsupported or not finite); original fp32 = its default fp32 run. Peak memory is the torch allocator's.
Accuracy
On public datasets
640x512 crops, the 7 most co-visible views as sources; GT = depth rendered from the structured-light points. AbsRel / delta1 over GT pixels, after per-image median scaling unless the model takes the cameras (calibrated MVS: cameras, error in mm; PatchMatchNet also the depth range 425-935 mm, MVSAnywhere its own range from the camera baselines). Original = the original code named under Details, same checkpoint and protocol.
| variant | dataset | original fp32 | original fp16 | portable | kernels | note |
|---|---|---|---|---|---|---|
mvsplat-re10k |
DTU scans 1, 9, 24, 33, 75, view 24 + 7 sources, AbsRel / delta1 % / MAE mm | 0.0438 / 97.31 / 31.17 | 0.0439 / 97.30 / 31.21 | 0.0438 / 97.30 / 31.20 | 0.0438 / 97.30 / 31.20 |
Measured on NVIDIA GeForce RTX 5060 Ti, torch 2.14.1+cu130, fastforks 28db82cb, 2026-11-13.
Parity with the original code
Every variant is checked against reference outputs of the original code at its pinned commit. CPU, float32: max |diff| <= 0.002 vs the original. GPU, float16 (the default), portable and kernels: mean |diff| <= 0.02 and p99 <= 0.25 (absolute error of the output depth).
Usage
from fastforks import multiview
model = multiview.load("mvsplat-re10k") # mode="auto": the preferred backend from recorded measurements
result = model(["view0.jpg", "view1.jpg", "view2.jpg"]) # the views of one scene, no cameras needed
result.depth # [V, H, W] float32 tensor; result.kind says what the maps mean
result.backend # what ran, e.g. Backend(mode='portable', device='cuda:0', dtype='float16')
Install with pip install fastforks (see https://github.com/kleinicke/fastforks). Other variants: mvsplat-re10k.
Kernels backend
multiview.load("mvsplat-re10k", mode="kernels") runs our CUDA kernels (cudnn_hacc). It needs a prebuilt kernel for your GPU architecture (downloaded from https://huggingface.co/fastforks/kernels on first use) and a recent NVIDIA driver; if there is none it raises BackendUnavailableError with the reason and never falls back silently. mode="auto" picks kernels when it can run and logs the choice.