DepthSplat
DepthSplat (ETH Zurich / cvg): 3D Gaussian splats and depth from several posed images in one pass; saves a 3DGS .ply. MIT (Small checkpoint).
experimental Fork of cvg/depthsplat@2dad25a · backends: portable, kernels
- Paper DepthSplat: Connecting Gaussian Splatting and Depth CVPR 2025 · first released 17 Oct 2024
Checkpoint depthsplat-small-re10k
Paper 2024 Added in 0.2.0 Evaluated with 0.2.0
Use it
pip install fastforks Lean install with only what this model needs: pip install fastforks-core
from fastforks import multiview
model = multiview.load("depthsplat-small-re10k") # kernels on a supported GPU, else portable PyTorch
result = model(images)
result.depth # also: confidence, gaussians
result.backend # what ran: mode, device, dtype, kernels fastforks bench depthsplat-small-re10k Times the model on this machine. load(…, mode="portable") or mode="kernels" picks a backend; usage guide.
Speed and memory
Every backend on one GPU (RTX 5060 Ti 16 GB) and the same input, the authors’ code included. Kernels runs fp16. Portable runs fp16 on CUDA.
Input: synthetic, 336x518
| Backend | dtype | Time per call (ms) | vs original fp16 | Peak memory allocated / reserved | Load (s) | First call (s) |
|---|---|---|---|---|---|---|
| Original fp32 | fp32 | not measured | – | – | – | – |
| Original fp16the authors' mixed-precision option (float16); cvg/depthsplat@2dad25a7b9ba EncoderDepthSplat, long side 256 | fp16 | 126 | – | 5,694 MiB/5,892 MiB | 0.5 | 0.35 |
| Portable fp32 | fp32 | not measured | – | – | – | – |
| Portable | fp16 | 119 | 1.1× | 5,432 MiB/5,606 MiB | 0.2 | 0.97 |
| Kernels | fp16 | 112 | 1.1× | 5,434 MiB/5,606 MiB | 1.1 | 0.80 |
| Portable + torch.compile | 82.2 | 1.5× | 5,432 MiB/5,526 MiB | 80 (build) | – | |
| TensorRT fp16 | fp16 | 86.4 | 1.5× | 2,952 MiBenginenot comparable | 224 (build) | – |
Measured on RTX 5060 Ti 16 GB, torch 2.14.1+cu130, 2026-11-12 to 2026-11-15. First call, 3 warm-up, peak reset, median of 3 rounds x median of 5. Ratios divide two
times of this table (same GPU, same input). Original fp16 is the authors’ own precision option, else torch.autocast. torch.compile and TensorRT: build time instead of load time. TensorRT memory (engine, not comparable) is the GPU memory the engine took, read from the driver because TensorRT allocates outside PyTorch, so it can't be compared with the PyTorch peaks of the other rows.
Other devices
| Device | Backend | dtype | ms / call | Peak memory | Output vs reference | Input |
|---|---|---|---|---|---|---|
| Apple M1 Pro 16 GB MPS, torch 2.14.1, 2026-11-14 | Original | fp32 | cannot run here | – | 336x518 | |
| Portable | fp16 | 757 | 8,900 MiB process | matches | 336x518 | |
| Portable | fp32 | 670 | 8,880 MiB process | matches | 336x518 | |
| Kernels | fp16 | not implemented | – | 336x518 | ||
CUDA memory is torch’s peak allocated / reserved; Apple has no such counter, so the Mac rows show the process footprint (weights, Python and torch included). “Output vs reference” compares the device’s output with the stored golden output under the card’s tolerance; – = not checked on that device. Kernels “not implemented” = no kernels for this model on that backend yet: it runs portable there.
Licence and weights
Commercial use allowed
- Only the Small RealEstate10K checkpoint is shipped: MIT code and weights, its monocular branch initialised from Depth Anything V2 Small (Apache-2.0). The Base / Large checkpoints build on Depth Anything V2 Base / Large (CC-BY-NC-4.0) and are not offered.
Our reading of the licences, not legal advice.
Weights
depthsplat-gs-small-re10k-256x256-view2-cfeab6b1.pth 154 MB· hosted on Hugging Facefastforks downloads and checks these files on first use (fastforks download depthsplat-small-re10k).
Accuracy
The test set through the authors’ code and through ours: same checkpoint, same protocol. The distance between the original’s fp32 and fp16 runs is what half precision alone costs; our runs should stay within it.
DTU scans 1
9, 24, 33, 75, view 24 + 7 sources, AbsRel / delta1 %
| Run | dtype | AbsRel ↓ | δ1.25 % ↑ | MAE mm ↓ | Δ AbsRel vs fp32 original | scans | ms / scan |
|---|---|---|---|---|---|---|---|
| Original fp32 | fp32 | 0.0992 | 98.72 | 66.52 | reference | 5 | 238 |
| Original fp16 | fp16 | 0.0974 | 98.69 | 65.37 | +0.0018 | 5 | 173 |
| Portable fp32 | fp32 | 0.0992 | 98.72 | 66.52 | ±0.0000 | 5 | 225 |
| Portable | fp16 | 0.0974 | 98.70 | 65.36 | +0.0018 | 5 | 164 |
| Kernels | fp16 | 0.0974 | 98.69 | 65.34 | +0.0018 | 5 | 155 |
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 authors’ code, same checkpoint and protocol. Measured on original fp32, original fp16: RTX 5060 Ti, torch 2.14.1+cu130, 2026-11-12; portable fp32, portable, kernels: RTX 5060 Ti, torch 2.14.1+cu130, fastforks 62af007c, 2026-11-12.
Closeness to the original
Beyond the test-set scores: the raw output of ours against the original’s fp32 output on the same input, pixel by pixel. CPU, float32: max |diff| <= 1.6e-05 vs the original. GPU, float16 (the default), portable and kernels: mean |diff| <= 0.0035 and p99 <= 0.017 (absolute error of the output depth).
| Check | Tolerance | Measured |
|---|---|---|
| CPU fp32, max |diff| | ≤ 0.000016 | not recorded |
| GPU default dtypes, mean |diff| | ≤ 0.0035 | 0.00197 |
| GPU default dtypes, p99 |diff| | ≤ 0.017 | 0.00899 |
Recorded for depthsplat-small-re10k on RTX 5060 Ti, torch 2.14.1+cu130, 2026-11-12, with these kernels: cudnn_haccfastbb
Details
DepthSplat (Xu et al. 2025): feed-forward 3D Gaussian splatting and depth from posed, calibrated images. A multi-view cost volume (UniMatch transformer, 2D U-Net) fused with a monocular DINOv2 ViT-S predicts every view's depth; a DPT feature upsampler and a Gaussian head predict one Gaussian per pixel (opacity, scale, rotation, degree-2 SH) in the given world frame (`result.gaussians`, `.save("scene.ply")`). Forward pass only: no renderer.
- Input / output
- 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.
- Input size
- any H x W >= 1, resized or padded inside the model; tested up to 3000x4000 (7,581 MiB allocated)
- Options
long_side=256>= 16· changes the output
- Outputs
depth,confidence,gaussians- CUDA kernels
fastbbfast backbone kernels: flash attention, window attention, instance norm and rotary embeddings for ViT and similar backbonescudnn_haccconvolutions with fp16 accumulation (cuDNN)
- Apple (MPS)
- fp32, fp16
Full reference, generated from the repository
DepthSplat (ETH Zurich / cvg): 3D Gaussian splats and depth from several posed images in one pass; saves a 3DGS .ply. MIT (Small checkpoint).
Commercial use: yes.
| variant | input | backend | time (ms) | peak memory (MiB, allocated / reserved) |
|---|---|---|---|---|
depthsplat-small-re10k | synthetic (336x518) | original portable kernels portable + torch.compile TensorRT fp16 | 126 119 112 82.2 86.4 | 5694 / 5892 5432 / 5606 5434 / 5606 5432 / 5526 3148 / 3194 |
Details
- Original code: https://github.com/cvg/depthsplat at
2dad25a - Code licence: MIT (permissive); files:
LICENSE - Weights licence: MIT
- Licence evidence: https://github.com/cvg/depthsplat/blob/2dad25a7b9ba7c5537aba08463ef88d8511a06be/LICENSE and https://github.com/cvg/depthsplat/blob/2dad25a7b9ba7c5537aba08463ef88d8511a06be/MODEL_ZOO.md and https://huggingface.co/haofeixu/depthsplat/tree/ed5116c11f7932fff3714989e2b65716730f6f87
- Training data: RealEstate10K (camera trajectories of YouTube real-estate videos) (RealEstate10K (YouTube videos, camera poses from ORB-SLAM; research use per its release), from a UniMatch depth / Depth Anything V2 Small initialisation.)
- Licence note: Only the Small RealEstate10K checkpoint is shipped: MIT code and weights, its monocular branch initialised from Depth Anything V2 Small (Apache-2.0). The Base / Large checkpoints build on Depth Anything V2 Base / Large (CC-BY-NC-4.0) and are not offered.
- Options:
long_side= 256 (>= 16) - Kernel libraries:
fastbb,cudnn_hacc - Variants:
depthsplat-small-re10k - Outputs: depth, confidence, gaussians; kind:
metric - Input size: any H x W >= 1, resized or padded inside the model
- Tested up to (portable, fp16, RTX 5060 Ti 16 GB):
depthsplat-small-re10k3000x4000 (7.4 GiB peak allocated, 8.6 reserved) depthsplat-small-re10k336x518, first call: portable + torch.compile 80 s (cold Inductor cache), TensorRT fp16 224 s (ONNX + engine).depthsplat-small-re10koriginal 336x518: the authors' mixed-precision option (float16); cvg/depthsplat@2dad25a7b9ba EncoderDepthSplat, long side 256depthsplat-small-re10kload / first call: original 1.83 s / 2.968 s (336x518), portable 0.22 s / 0.968 s (336x518), kernels 1.47 s / 0.71 s (336x518)- Protocol, first call, 3 warm-up, peak reset, median of 3 rounds x median of 5
Measured
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 | portable fp32 | kernels | note |
|---|---|---|---|---|---|---|---|
depthsplat-small-re10k | DTU scans 1, 9, 24, 33, 75, view 24 + 7 sources, AbsRel / delta1 % / MAE mm | 0.0992 / 98.72 / 66.52 | 0.0974 / 98.69 / 65.37 | 0.0974 / 98.70 / 65.36 | 0.0992 / 98.72 / 66.52 | 0.0974 / 98.69 / 65.34 |
Measured on NVIDIA GeForce RTX 5060 Ti, torch 2.14.1+cu130, fastforks 62af007c, 2026-11-12.
Parity
CPU, float32: max |diff| <= 1.6e-05 vs the original. GPU, float16 (the default), portable and kernels: mean |diff| <= 0.0035 and p99 <= 0.017 (absolute error of the output depth).
| variant | kernels error vs original, mean / p99 | GPU, torch | kernels used |
|---|---|---|---|
depthsplat-small-re10k | 0.00197 / 0.00899 | RTX 5060 Ti, torch 2.14.1+cu130 | cudnn_hacc@cudnn92400, fastbb@7d058322634d:sm_120 |
Example output
No example rendered for this checkpoint yet.