LingBot-Map
LingBot-Map (Robbyant, 2026): streaming 3D reconstruction, cameras and depth for a long image sequence frame by frame with a sliding-window cache. Apache-2.0 code and weights.
experimental Fork of Robbyant/lingbot-map@b9dd1b1 · backends: portable, kernels
- Paper LingBot-Map: Geometric Context Transformer for Streaming 3D Reconstruction ECCV 2026 · first released 15 Apr 2026
Checkpoint lingbot-map
Paper 2026 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("lingbot-map") # kernels on a supported GPU, else portable PyTorch
result = model(images)
result.depth # also: confidence, intrinsics, cam_to_world
result.backend # what ran: mode, device, dtype, kernels fastforks bench lingbot-map 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, 480x640
| 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); upstream GCTStream.inference_streaming (demo defaults, SDPA), bfloat16 aggregator | bf16 | 993 | – | 7,141 MiB/7,672 MiB | 11.5 | 2.48 |
| Portable fp32 | fp32 | not measured | – | – | – | – |
| Portable | fp16 | 730 | 1.4× | 4,512 MiB/4,770 MiB | 6.6 | 1.08 |
| Kernels | fp16 | 515 | 1.9× | 4,519 MiB/4,810 MiB | 5.7 | 0.84 |
| Portable + torch.compileplanned for 0.2.1 | fails | – | – | – | – | |
| TensorRT fp16 | fp16 | 489 | 2.0× | 3,550 MiBenginenot comparable | 181 (build) | – |
Measured on RTX 5060 Ti 16 GB, torch 2.14.1+cu130, 2026-11-15 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, 2026-11-17 | Portable | fp16 | 7125 | 8,834 MiB process | skip | 480x640 |
| Portable | fp32 | 8840 | 12.7 GiB process | skip | 480x640 | |
| Kernels | fp16 | not implemented | – | 480x640 | ||
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
- Code
- Apache-2.0 LICENSE
- Weights
- Apache-2.0 source
- Training data
- Per the README: a stage-1 bidirectional (VGGT-style) checkpoint, then streaming training; datasets are not listed
Our reading of the licences, not legal advice.
Weights
lingbot-map.pt 4.6 GB· hosted on Hugging Facefastforks downloads and checks these files on first use (fastforks download lingbot-map).
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 | 0.0304 | 97.30 | reference | 5 | 3284 |
| Original fp16 | not measured | |||||
| Portable fp32 | fp32 | 0.0304 | 97.30 | ±0.0000 | 5 | 3197 |
| Portable | fp16 | 0.0305 | 97.28 | −0.0001 | 5 | 788 |
| Kernels | fp16 | 0.0304 | 97.33 | ±0.0000 | 5 | 556 |
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: RTX 5060 Ti, torch 2.14.1+cu130, 2026-11-16; 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 68b2f345, 2026-11-16.
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 | 0.00042 |
| GPU default dtypes, p99 |diff| | ≤ 0.25 | 0.00121 |
Recorded for lingbot-map on RTX 5060 Ti, torch 2.14.1+cu130, 2026-11-14, with these kernels: cudnn_haccfastbb
Details
LingBot-Map (Robbyant, 2026): streaming 3D reconstruction. A VGGT-style aggregator (DINOv2 ViT-L patch embed, 24 frame / global attention blocks, 3D RoPE) runs causally over the views in order with a KV cache (scale frames + a sliding window), then a camera head and a DPT depth head give cameras and depth of every view.
- 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 (5,593 MiB allocated)
- Options
long_side=518>= 14· changes the outputscale_frames=8>= 1· changes the outputwindow=64>= 1· changes the output
- Outputs
depth,confidence,intrinsics,cam_to_world- 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
Limitations
- Views are a sequence (a video): each view only sees the first `scale_frames` views and the views before it (older than `window` frames: their 6 special tokens only). At most 1024 views.
Full reference, generated from the repository
LingBot-Map (Robbyant, 2026): streaming 3D reconstruction, cameras and depth for a long image sequence frame by frame with a sliding-window cache. Apache-2.0 code and weights.
Commercial use: yes.
| variant | input | backend | time (ms) | peak memory (MiB, allocated / reserved) |
|---|---|---|---|---|
lingbot-map | synthetic (480x640) | original portable kernels portable + torch.compile TensorRT fp16 | 993 730 515 planned for 0.2.1 489 | 7141 / 7672 4512 / 4770 4519 / 4810 – 6280 / 6338 |
Details
- Original code: https://github.com/Robbyant/lingbot-map at
b9dd1b1 - Code licence: Apache-2.0 (permissive); files:
LICENSE - Weights licence: Apache-2.0
- Licence evidence: https://github.com/Robbyant/lingbot-map/blob/b9dd1b1/LICENSE.txt and https://huggingface.co/robbyant/lingbot-map (no licence field)
- Training data: Per the README: a stage-1 bidirectional (VGGT-style) checkpoint, then streaming training; datasets are not listed
- Options:
long_side= 518 (>= 14),scale_frames= 8 (>= 1),window= 64 (>= 1) - Kernel libraries:
fastbb,cudnn_hacc - Variants:
lingbot-map - Not in this release (planned for 0.2.1):
lingbot-mapcompile(): Inductor fails to compile a fused Triton kernel (cat / cos / sin) - Outputs: depth, confidence, intrinsics, 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):
lingbot-map3000x4000 (5.5 GiB peak allocated, 6.8 reserved) lingbot-map480x640, first call: TensorRT fp16 181 s (ONNX + engine).lingbot-maporiginal 480x640: the authors' mixed-precision option (bfloat16); upstream GCTStream.inference_streaming (demo defaults, SDPA), bfloat16 aggregatorlingbot-mapload / first call: original 131.28 s / 4.645 s (480x640), portable 6.58 s / 1.077 s (480x640), kernels 5.69 s / 0.843 s (480x640)- 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 | portable | portable fp32 | kernels | note |
|---|---|---|---|---|---|---|
lingbot-map | DTU scans 1, 9, 24, 33, 75, view 24 + 7 sources, AbsRel / delta1 % | 0.0304 / 97.30 | 0.0305 / 97.28 | 0.0304 / 97.30 | 0.0304 / 97.33 |
Measured on portable: NVIDIA GeForce RTX 5060 Ti, torch 2.14.1+cu130, fastforks 68b2f345, 2026-11-16; 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 68b2f345, 2026-11-16.
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 |
|---|---|---|---|
lingbot-map | 0.00042 / 0.00121 | RTX 5060 Ti, torch 2.14.1+cu130 | cudnn_hacc@cudnn92400, fastbb@7d058322634d:sm_120 |
Limitations
- Views are a sequence (a video): each view only sees the first
scale_framesviews and the views before it (older thanwindowframes: their 6 special tokens only). At most 1024 views.
Example output
No example rendered for this checkpoint yet.