Pi3
π3 (Pi3, yyfz): cameras, depth and 3D points from many unposed images in one pass, with no reference view. Non-commercial weights.
experimental Fork of yyfz/Pi3@9fa3ddb · backends: portable, kernels
- Paper π³: Permutation-Equivariant Visual Geometry Learning ICLR 2026 · first released 17 Jul 2025
Checkpoint pi3
Paper 2025 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("pi3") # kernels on a supported GPU, else portable PyTorch
result = model(images)
result.depth # also: confidence, world_points, cam_to_world
result.backend # what ran: mode, device, dtype, kernels The weights are non-commercial: fastforks downloads them only with FASTFORKS_NONCOMMERCIAL=1 set.
fastforks bench pi3 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 (own default)the authors' mixed-precision option (bfloat16); yyfz/Pi3@9fa3ddb3f8d5 Pi3.forward, PIXEL_LIMIT 255000 | bf16 | 1057 | – | 5,926 MiB/6,016 MiB | 9.1 | 1.15 |
| Portable fp32 | fp32 | not measured | – | – | – | – |
| Portable | fp16 | 821 | 1.3× | 2,360 MiB/2,416 MiB | 3.5 | 1.28 |
| Kernels | fp16 | 559 | 1.9× | 2,367 MiB/2,456 MiB | 3.8 | 0.70 |
| Portable + torch.compile | 752 | 1.4× | 2,205 MiB/2,334 MiB | 56 (build) | – | |
| TensorRTplanned for 0.2.1 | fails | – | – | – | – |
Measured on RTX 5060 Ti 16 GB, torch 2.14.1+cu130, 2026-11-13 to 2026-11-16. 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, 2026-11-13 | Original | fp32 | 10379 | 6,238 MiB process | – | 336x518 |
| Portable | fp16 | 8341 | 6,510 MiB process | matches | 336x518 | |
| Portable | fp32 | 10298 | 6,201 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
Non-commercial only
- Code
- BSD-3-Clause LICENSE
- Weights
- CC-BY-NC-4.0 source
- Training data
- Per the paper (arXiv 2507.13347): a mixture of public synthetic and real multi-view datasets; DINOv2 initialisation. The README restricts the weights to non-commercial use because of the training datasets.
- weights: CC-BY-NC-4.0
- The Pi3 code is BSD-3-Clause, but the README licenses the Pi3 weights CC-BY-NC-4.0 (non-commercial); the Hugging Face card's bsd-2-clause tag is overridden by that statement.
Our reading of the licences, not legal advice.
Weights
model.safetensors 3.8 GB· hosted on Hugging Facefastforks downloads and checks these files on first use (fastforks download pi3). Non-commercial weights need FASTFORKS_NONCOMMERCIAL=1.
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 % ↑ | Δ AbsRel vs fp32 original | scans | ms / scan |
|---|---|---|---|---|---|---|
| Original fp32 | fp32 | 0.0070 | 99.94 | reference | 5 | 3605 |
| Original fp16 | bf16 | 0.0071 | 99.94 | −0.0001 | 5 | 1022 |
| Portable fp32 | fp32 | 0.0070 | 99.94 | ±0.0000 | 5 | 3602 |
| Portable | fp16 | 0.0070 | 99.94 | ±0.0000 | 5 | 823 |
| Kernels | fp16 | 0.0070 | 99.94 | ±0.0000 | 5 | 562 |
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, 2026-11-13; portable fp32: RTX 5060 Ti, torch 2.14.1+cu130, fastforks 30c7a8e9, 2026-11-17; portable, kernels: RTX 5060 Ti, torch 2.14.1+cu130, fastforks 28db82cb, 2026-11-13.
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| <= 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).
| Check | Tolerance | Measured |
|---|---|---|
| CPU fp32, max |diff| | ≤ 0.002 | not recorded |
| GPU default dtypes, mean |diff| | ≤ 0.02 | 0.00107 |
| GPU default dtypes, p99 |diff| | ≤ 0.25 | 0.00237 |
Recorded for pi3 on RTX 5060 Ti, torch 2.14.1+cu130, 2026-11-13, with these kernels: fastbb
Details
π³, permutation-equivariant visual geometry learning (Wang et al. 2025): cameras, depth and point maps of every view from unposed images in one forward pass, with no reference view. A DINOv2 ViT-L/14 encoder feeds 36 alternating frame / global attention blocks (q/k norm, 2-D RoPE); three small transformer decoders give local point maps, confidences and camera poses.
- 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 (4,896 MiB allocated)
- Options
pixel_limit=255000>= 196· changes the output
- Outputs
depth,confidence,world_points,cam_to_world- CUDA kernels
fastbbfast backbone kernels: flash attention, window attention, instance norm and rotary embeddings for ViT and similar backbones
- Apple (MPS)
- fp32, fp16
Full reference, generated from the repository
π3 (Pi3, yyfz): cameras, depth and 3D points from many unposed images in one pass, with no reference view. Non-commercial weights.
Commercial use: no (weights: CC-BY-NC-4.0).
| variant | input | backend | time (ms) | peak memory (MiB, allocated / reserved) |
|---|---|---|---|---|
pi3 | synthetic (336x518) | original portable kernels portable + torch.compile TensorRT fp16 | 1057 821 559 752 planned for 0.2.1 | 5926 / 6016 2360 / 2416 2367 / 2456 2205 / 2334 – |
Details
- Original code: https://github.com/yyfz/Pi3 at
9fa3ddb - Code licence: BSD-3-Clause (permissive); files:
LICENSE - Weights licence: CC-BY-NC-4.0
- Licence evidence: https://github.com/yyfz/Pi3/blob/9fa3ddb/LICENSE and https://github.com/yyfz/Pi3/blob/9fa3ddb/README.md#-license
- Training data: Per the paper (arXiv 2507.13347): a mixture of public synthetic and real multi-view datasets; DINOv2 initialisation. The README restricts the weights to non-commercial use because of the training datasets.
- Licence note: The Pi3 code is BSD-3-Clause, but the README licenses the Pi3 weights CC-BY-NC-4.0 (non-commercial); the Hugging Face card's bsd-2-clause tag is overridden by that statement.
- Options:
pixel_limit= 255000 (>= 196) - Kernel libraries:
fastbb - Variants:
pi3 - Not in this release (planned for 0.2.1):
pi3ONNX / TensorRT export: the ONNX converter fails on the exported program (ConversionError, step 3/3) - Outputs: depth, confidence, world_points, cam_to_world; kind:
scale_invariant - Input size: any H x W >= 1, resized or padded inside the model
- Tested up to (portable, fp16, RTX 5060 Ti 16 GB):
pi33000x4000 (4.8 GiB peak allocated, 6.5 reserved) pi3336x518, first call: portable + torch.compile 56 s (cold Inductor cache).pi3original 336x518: the authors' mixed-precision option (bfloat16); yyfz/Pi3@9fa3ddb3f8d5 Pi3.forward, PIXEL_LIMIT 255000pi3load / first call: original 10.64 s / 4.059 s (336x518), portable 3.46 s / 1.284 s (336x518), kernels 3.78 s / 0.7 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 |
|---|---|---|---|---|---|---|---|
pi3 | DTU scans 1, 9, 24, 33, 75, view 24 + 7 sources, AbsRel / delta1 % | 0.0070 / 99.94 | 0.0071 / 99.94 | 0.0070 / 99.94 | 0.0070 / 99.94 | 0.0070 / 99.94 |
Measured on portable: NVIDIA GeForce RTX 5060 Ti, torch 2.14.1+cu130, fastforks 28db82cb, 2026-11-13; portable32: NVIDIA GeForce RTX 5060 Ti, torch 2.14.1+cu130, fastforks 30c7a8e9, 2026-11-17; kernels: NVIDIA GeForce RTX 5060 Ti, torch 2.14.1+cu130, fastforks 28db82cb, 2026-11-13.
Parity
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).
| variant | kernels error vs original, mean / p99 | GPU, torch | kernels used |
|---|---|---|---|
pi3 | 0.00107 / 0.00237 | RTX 5060 Ti, torch 2.14.1+cu130 | fastbb@7d058322634d:sm_120 |
Example output
No example rendered for this checkpoint yet.