ReSplat (fastforks)
ReSplat (Xu et al. 2025): feed-forward 3D Gaussian splatting from posed, calibrated images with recurrent refinement. DepthSplat's multi-view depth network (cost volume + DINOv2) and a kNN point transformer predict latent Gaussians (SH degree 3); refinement steps render the input views, compare them with the images (ResNet-18 features + colour) and update every Gaussian with a second point transformer. Returns every view's depth and the Gaussians in the given world frame (result.gaussians, .save("scene.ply")).
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/cvg/resplat at cae7ddc.
Author weight repos: https://huggingface.co/haofeixu/resplat.
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 |
|---|---|---|---|---|
resplat-base-re10k@1 |
resplat-base-re10k-256x256-view2-b90d1b53.pth | b90d1b530042 |
CC-BY-NC-4.0 | no |
resplat-small-dl3dv@1 |
resplat-small-dl3dv-256x448-view8-548993fe.pth | 548993fede0d |
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: DL3DV-10K (multi-view real-world scenes for 3D vision) (DL3DV-10K (non-commercial research licence), from DepthSplat / Depth Anything V2 Small depth initialisations.).
- Licence note: Code and checkpoints are MIT. The Base RealEstate10K checkpoint's monocular branch is initialised from Depth Anything V2 Base (CC-BY-NC-4.0) and is labelled non-commercial; the Small DL3DV checkpoint builds on Depth Anything V2 Small (Apache-2.0).
Licence evidence: https://github.com/cvg/resplat/blob/cae7ddc/LICENSE and https://github.com/cvg/resplat/blob/cae7ddc/MODEL_ZOO.md and https://huggingface.co/haofeixu/resplat/tree/c69ad72a49b8358ac46599cf74468090425ed9c7
Input size
any H x W >= 1, resized or padded inside the model
Tested up to (portable, fp16, RTX 5060 Ti 16 GB): resplat-base-re10k 3000x4000 (7.8 GiB peak allocated, 11.2 reserved); resplat-small-dl3dv 3000x4000 (5.9 GiB peak allocated, 7.0 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 |
|---|---|---|---|---|---|---|---|---|---|---|
resplat-small-dl3dv |
480x640 | β | β | 1723 | β | β | β | β | 4995 / 5180 | β |
Startup and first call
| model | load (s): original | portable | kernels | first call (s): original | portable | kernels |
|---|---|---|---|---|---|---|
resplat-small-dl3dv |
β | 0.72 (480x640) | β | β | 2.51 (480x640) | β |
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) |
|---|---|---|---|---|---|---|---|---|---|---|---|
resplat-small-dl3dv |
480x640 | 1723 ms | deferred (build >5 min) | planned for 0.2.1 | β | β | β | 4995 / 5180 | β | β | 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
Parity with the original code
Every variant is checked against reference outputs of the original code at its pinned commit. CPU, float32: max |diff| <= 5e-05 vs the original. GPU, float16 (the default), portable and kernels: mean |diff| <= 0.01 and p99 <= 0.05 (absolute error of the output depth).
Usage
from fastforks import multiview
# non-commercial weights: run with FASTFORKS_NONCOMMERCIAL=1 in the environment
model = multiview.load("resplat-base-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: resplat-base-re10k, resplat-small-dl3dv.
Kernels backend
multiview.load("resplat-base-re10k", mode="kernels") runs our CUDA kernels (fastbb, cudnn_hacc, gsraster). 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.