Cross3DGS: Unified Vulkan-Based 3D Gaussian Splatting Training from Workstations to Mobile Devices
Organizations: MinD in a Device Co., Ltd., Tokyo, Japan · Independent Researcher, Kanagawa, Japan
Abstract
Scenes captured with handheld and wearable cameras are still shipped to a CUDA workstation for 3D Gaussian Splatting (3DGS) training. Training on the device that captured them, or on its companion phone or laptop, requires more than translating kernels: GPUs and drivers differ in parallel features, memory limits, and command submission, and these differences decide whether a training schedule executes and returns the correct update. We present Cross3DGS, a cross-vendor, cross-platform Vulkan trainer that keeps one optimizer and chooses its execution schedule per device in two steps: rules on device limits, workload size, and observed driver failures exclude the schedules known not to run correctly, and a fixed preference order selects one of the remaining feasible schedules. The same core completes standard-quality training (30k updates, one million Gaussians) on every configuration we measured, spanning NVIDIA, Intel, Arm, Qualcomm, AMD, and Apple GPUs and including Android devices and an iPhone, whereas the existing portable trainers VkSplat and Brush do not run on some of the mobile GPUs. Averaged over 11 scenes on a workstation, Cross3DGS has higher quality than VkSplat with no significant difference in training time, and Brush reports about three times the training time at comparable quality. The final quality of Cross3DGS is nearly identical across devices. A mobile application turns a handheld capture into a viewable model entirely on the device.
Figures & tables
| moved to a later value by | |||||
|---|---|---|---|---|---|
| option | # | values | device limit | workload | driver failure |
| gradient method (work assignment + merge) | 8 | tiled + native atomic, tiled + CAS, pixel/subgroup + native atomic, pixel/subgroup + CAS, per-splat + native atomic, per-splat + CAS, pair-partial + fixed reduction (exact pair gather), per-splat + fixed reduction (pair reduction) | subgroup width, shared memory, float32 atomic add | – | scatter failures |
| command submission | 2 | batched (8 updates), fenced (per pass) | – | – | watchdog timeout |
| training images | 2 | resident (all in GPU memory), streamed (one per update) | – | images exceed one storage buffer | device fault |
| radix sort | 2 | subgroup, portable | – | – | corrupted sort keys |
| projection and Adam | 2 | fused, split | buffer bindings | SH coefficients exceed one storage buffer | – |
| vendor | NVIDIA | Intel | Intel | Arm | Qualcomm | AMD | Apple † | Apple † | |
|---|---|---|---|---|---|---|---|---|---|
| product | PRO6000 [ 49 ] | Iris Xe [ 30 ] | UHD730 [ 31 ] | Mali G1-Ultra [ 6 ] | Adreno740 [ 51 ] | RX9070XT [ 2 ] | M5Pro [ 4 ] | A14 [ 3 ] | |
| launch year | 2025 | 2023 | 2024 | 2025 | 2022 | 2025 | 2026 | 2020 | |
| host | Windows workstation | Windows laptop iGPU | Ubuntu desktop iGPU | Android phone | Android tablet | Ubuntu desktop | macOS laptop | iOS phone | |
| memory (GB) | 96 | 16 | 16 | 12 | 12 | 16 | 48 | 6 | |
| Device limits | subgroup width | 32 | 32 | 32 | 16 | 64 | 64 | 32 | 32 |
| max shared memory (KiB) | 48 | 32 | 64 | 32 | 32 | 64 | 32 | 32 |
| feasible | same GPU | CPU double | ||||
|---|---|---|---|---|---|---|
| configuration | methods | viol. | ||||
| PRO6000 | 8 | 0 | ||||
| Iris Xe | 4 | 0 | ||||
| UHD730 | 5 | 0 | ||||
| G1-Ultra | 4 | 0 | ||||
| Adreno740 | 3 | 0 | ||||
| configuration | bicycle | garden |
|---|---|---|
| PRO6000 | 25.30/0.767/0.196 | 27.01/0.852/0.108 |
| Iris Xe | 25.28/0.766/0.196 | 26.99/0.852/0.108 |
| UHD730 | 25.30/0.767/0.196 | 27.02/0.852/0.108 |
| G1-Ultra | 25.30/0.767/0.195 | 27.00/0.852/0.108 |
| Adreno740 | 25.29/0.767/0.196 | 26.97/0.852/0.108 |
| RX9070XT | 25.30/0.767/0.196 | 27.03/0.852/0.107 |
| Cross3DGS | VkSplat | Brush | ||||
| scene | P /S /L | s | P /S /L | s | P /S /L | s |
| Mip-NeRF 360 | ||||||
| bicycle | 25.30 /.767/.196 | 115.1 | 25.11/.760/.201 | 114.5 | 25.15/ .769 / .188 | 425 |
| garden | 27.01/.852/.108 | 110.0 | 26.95/.848/.114 | 106.3 | 27.21 / .855 / .098 | 387 |
| stump | 26.84 / .786 / .163 | 110.0 | 26.63/.779/.171 | 113.4 | 26.42/.776/.166 | 397 |
| bonsai | 32.35/ .947 /.120 | 171.8 | 32.56/ .947 /.119 | 175.2 | 32.78 / .947 / .117 | 440 |
| demonstration preset | standard quality | ||||||
| plush toy | plush toy | plush toy | shrine | statue | shrine | statue | |
| device | A14 | G1-Ultra | Adreno740 | G1-Ultra | G1-Ultra | G1-Ultra | G1-Ultra |
| updates/cap. | 3k/250k | 3k/250k | 3k/250k | 3k/250k | 3k/250k | 30k/1M | 30k/1M |
| registered | 100/100 | 100/100 | 100/100 | 100/100 | 99/100 | 100/100 | 99/100 |
| train/held-out | 87/13 | 87/13 | 87/13 | 87/13 | 86/13 | 87/13 | 86/13 |
| seed points | 62,127 | 95,814 | 66,912 | 54,676 | 36,784 | 54,676 | 36,784 |
Appendix figures & tables13 assets
Supplementary material from the paper’s appendix.
Appendix
| setting | value |
|---|---|
| updates | 30,000, one training image per update |
| view sampling | uniform with replacement, seeded |
| loss | ; SSIM with an Gaussian window ( ), , , zero padding, mean over the full image |
| SH degree | 3; the active degree is at update |
| capacity | 1,000,000 Gaussians |
| initialization | SfM points; scale the root-mean-square distance to the three nearest points; opacity 0.5; random unit quaternion; SH DC from the point color, higher SH zero |
| method | reported time | included | excluded |
|---|---|---|---|
| Cross3DGS | sum over training calls of the host wall time ( steady_clock ) from issuing execute (one update) or executeBatch (eight) to its return | all 30,000 updates; the host waits for each submission (eight updates when batched, one pass when fenced) before issuing the next | scene loading, pipeline and shader setup, validation, render and PLY export, evaluation, and viewer readback |
| VkSplat | sum over updates of the host wall time ( perf_counter ) around each train_step call | all 30,000 updates | the same |
| Brush | the training time its command-line interface reports, in whole seconds | what its training loop counts | not controllable from outside |
| PSNR (dB) | training time (s) | ||||||
|---|---|---|---|---|---|---|---|
| scene | seed | Cross3DGS | VkSplat | Brush | Cross3DGS | VkSplat | Brush |
| bicycle | 20260815 | 25.31 | 25.11 | 25.18 | 114.2 | 114.4 | 425 |
| 20260816 | 25.30 | 25.11 | 25.15 | 115.3 | 114.8 | 425 | |
| 20260817 | 25.26 | 25.11 | 25.14 | 115.1 | 114.5 | 426 | |
| garden | 20260815 | 27.09 | 26.98 | 27.21 | 110.3 | 106.3 | 386 |
| 20260816 | 26.99 | 26.92 | 27.27 | 109.9 | 105.8 | 388 | |
| kind | option | rule | a schedule fails when | value instead |
| device limit | gradient method | SUBGROUP-TILED | it uses the tiled assignment and the subgroup width is below 8 or shared memory is below 49,152 bytes | a later gradient method |
| gradient method | ATOMIC-NATIVE | it merges with native atomics and the device lacks float32 atomic add | CAS or fixed reduction | |
| projection and Adam | BINDING-FUSED | it fuses projection and Adam and a stage may bind fewer than 26 storage buffers | split | |
| radix sort | RADIX-SHARED | the radix histogram, bytes for subgroup width , exceeds shared memory | none: training is refused | |
| pair dispatch | DISPATCH-INDIRECT-FEATURE | it dispatches pairs indirectly and the runtime’s indirect-dispatch flag is off | direct | |
| workload | training images | DESCRIPTOR-TARGET-RANGE | it keeps images resident and width height views 4 bytes exceeds the storage-buffer range | streamed |
| option | rule | cause: the excluded value that was run | result |
|---|---|---|---|
| gradient method | ATOMIC-SCATTER-QCOM | a gradient pass merging with CAS | scatter failure: the pass timed out and the device was lost ( VK_ERROR_DEVICE_LOST ) |
| command submission | SUBMISSION-BATCHED-QCOM | batched submission | watchdog timeout: the run did not finish and was stopped by a 480 s watchdog |
| training images | TARGET-RESIDENT-QCOM | all training images resident, the current target copied with vkCmdCopyBuffer | device fault: the second update faulted, the device was lost, and the tablet restarted |
| radix sort | RADIX-SUBGROUP-QCOM | subgroup radix sort | corrupted sort keys: of 17,624 sorted entries, 3,727 out of order and 8,580 with wrong keys or values |
| configuration | vendor identity | storage-buffer bindings |
|---|---|---|
| PRO6000 | 0x10DE | 1,048,576 |
| Iris Xe | 0x8086 | 200 |
| UHD730 | 0x8086 | 201,326,592 |
| G1-Ultra | 0x13B5 | 8,388,608 |
| Adreno740 | 0x5143 | 16,777,216 |
| RX9070XT | 0x1002 | 8,388,606 |
| configuration | operating system | GPU driver | Vulkan API (device) |
|---|---|---|---|
| PRO6000 | Windows 11 (10.0.26200) | NVIDIA 596.72 | 1.4.329 |
| Iris Xe | Windows 11 Home (10.0.26200) | Intel 32.0.101.7085 | 1.4.323 |
| UHD730 | Ubuntu 24.04.5, Linux 7.0.0-38 | Mesa ANV 25.2.8 (0ubuntu0.24.04.4) | 1.4.318 a |
| G1-Ultra | Android 16, HyperOS 3.0.305 b | Arm r54p1 b | 1.3.305 b |
| Adreno740 | Android 16, HyperOS 3.0.305 | Qualcomm 0676.76.1 c | 1.3.128 |
| RX9070XT | Ubuntu 24.04.5, Linux 7.0.0-38 | Mesa RADV 25.2.8 (0ubuntu0.24.04.4) | 1.4.318 a |
| rank | common | AMD | Intel |
|---|---|---|---|
| 1 | tiled + native | per-splat + CAS | tiled + native |
| 2 | tiled + CAS | exact pair gather | pixel + native |
| 3 | pixel + native | per-splat + native | per-splat + native |
| 4 | pixel + CAS | pair reduction | pixel + CAS |
| 5 | per-splat + native | pixel + CAS | exact pair gather |
| 6 | per-splat + CAS | pixel + native | pair reduction |
| configuration | selected method | fastest method | slowdown |
|---|---|---|---|
| M5Pro | pixel/subgroup + native | pixel/subgroup + native | 1.00 |
| A14 | pixel/subgroup + native | pixel/subgroup + native | 1.00 |
| 3DGS only | capture-to-view | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|
| temp. | temp. | ||||||||||
| device | policy | GPU | step | GPU | battery | CPU | GPU | SfM | 3DGS | GPU | battery |
| G1-Ultra | spec | 2.70 / 3.50 / 4.21 | 1.72 b | ||||||||
| AnTuTu | 2.70 / 3.50 / 4.21 | 1.72 | |||||||||
| default | 0.65 | 1 | 45.3 | 32.2 | 1.08 / 1.47 / 1.74 | 0.57 | 27.1 | 7.8 | 53.6 | 40.9 | |
| Game Turbo | 0.56 | 0.86 | 44.6 | 33.0 | 1.17 / 2.11 / 2.17 | 0.56 | 18.9 | 7.9 | 58.0 | 43.9 | |
| GPU (°C) | battery (°C) | |||||||||
|---|---|---|---|---|---|---|---|---|---|---|
| device | power | Fig. 6 | peak | at launch | peak | time (h) | energy (Wh) | mean (W) | battery (%) | GPU clock |
| Adreno740 | battery | a, b, c, e | 57.0 | 32.9 | 37.4 | 2.82 | 16.9 | 6.0 | 100 54 | 0.55 GHz throughout |
| external | a, b, c | 57.9 | 32.9 | 36.7 | 2.83 | – | – | 91 84 | 0.55 GHz throughout | |
| G1-Ultra | battery | a–e | 55.5 | 29.9 | 41.2 | 2.45 | 7.2 | 3.0 | 100 77 | 0.60 GHz from 19.8k updates |
| external | a–d | 56.1 | 30.3 | 41.3 | 2.44 | – | – | 100 100 | 0.60 GHz from 16.1k updates | |
| A14 | battery | c, e | – | – | – | 2.80 | 9.2 a | 4.2 a | 100 15 | not reported by iOS |
| GPU (°C) | battery (°C) | |||||
|---|---|---|---|---|---|---|
| device | at launch | peak | at launch | peak | thermal state | total (min) |
| A14 | – | – | – | – | nominal serious | 45.9 |
| G1-Ultra | 45.2 | 66.5 | 32.4 | 41.8 | normal | 35.3 |
| Adreno740 | 42.8 | 70.8 | 32.7 | 37.7 | normal | 37.5 |