LIVE
Google Introduces "Gemini 4 Carbon" as Next Step in Its Model Lineup28/10/26 · Google|DeepMind unveils Genie 4, a new generation of world model27/10/26 · Google DeepMind|Anthropic files IPO prospectus, with risk disclosures taking center stage26/10/26 · Anthropic|Robot policy trained only in simulation matches top real-world systems26/10/26|OpenAI unveils GPT-6.1 Terra, a model built for computer use26/10/26 · OpenAI|Google's AI gives evasive answers about who won the 2020 US election28/10/26 · Google|NVIDIA introduces Nemotron 3.5 Transcribe, a promptable multilingual transcription model28/10/26 · NVIDIA|OpenAI and ServiceNow deepen partnership on enterprise workflows28/10/26 · OpenAI|Failed startups' data finds a second life training AI models28/10/26|Anthropic expands AI for Science program to 20 foundations and research institutions28/10/26 · Anthropic|Anthropic shares early results on using Claude to accelerate drug development27/10/26 · Anthropic|GEPA-Curator: Filtering Failures to Better Train LLM Agents27/10/26|Google Introduces "Gemini 4 Carbon" as Next Step in Its Model Lineup28/10/26 · Google|DeepMind unveils Genie 4, a new generation of world model27/10/26 · Google DeepMind|Anthropic files IPO prospectus, with risk disclosures taking center stage26/10/26 · Anthropic|Robot policy trained only in simulation matches top real-world systems26/10/26|OpenAI unveils GPT-6.1 Terra, a model built for computer use26/10/26 · OpenAI|Google's AI gives evasive answers about who won the 2020 US election28/10/26 · Google|NVIDIA introduces Nemotron 3.5 Transcribe, a promptable multilingual transcription model28/10/26 · NVIDIA|OpenAI and ServiceNow deepen partnership on enterprise workflows28/10/26 · OpenAI|Failed startups' data finds a second life training AI models28/10/26|Anthropic expands AI for Science program to 20 foundations and research institutions28/10/26 · Anthropic|Anthropic shares early results on using Claude to accelerate drug development27/10/26 · Anthropic|GEPA-Curator: Filtering Failures to Better Train LLM Agents27/10/26|
AppWatch outofficial publisher

Postshot (Jawset)

App : A product you use directly

Local Gaussian splat training on NVIDIA GPU.

The local reference for Gaussian splatting; export has moved to a subscription model.

Overall score
7.5 /10
Security: nothing to flag
Utility
7.5
Reliability
6.0
Security
No caveat on record
Ease
5 min · Comfortable

Security reflects where data goes, requested permissions and incidents on record at the verification date. It is not a guarantee of zero risk: check the deployment mode and the connections you enable.

What it does, concretely

Creating photorealistic 3D models from simple photos or videos usually requires complex tools, specialized hardware, or cloud services that retain your data. Postshot addresses this by enabling full 3D scene reconstruction directly on your computer, with nothing sent outside.

The software uses radiance field technology, specifically Gaussian splatting, to learn the geometry and appearance of a scene from a set of images. You simply provide photos or a video, and Postshot automatically handles pose alignment and model training, entirely on your local NVIDIA GPU.

Postshot is aimed at 3D content creators, visual production teams, and developers who need to integrate reconstructed scenes into tools such as Unreal Engine or After Effects. Local processing and full content ownership make it a suitable choice for sensitive or confidential projects.

However, the software is limited to Windows and requires a recent NVIDIA GPU (RTX 2060 or higher). Users on macOS, Linux, or with AMD or Intel graphics cards cannot use it. Exporting models to third-party viewers requires a paid subscription.

What it offers

  • ·Automatic 3D reconstruction from photos or videos (JPG, PNG, TIF, EXR, DNG, RAW, MOV, MP4, MKV) without specialized hardware.
  • ·Fully local training on NVIDIA GPU: no data leaves your machine.
  • ·Live training preview to monitor model progress in real time.
  • ·Image masking to remove unwanted elements such as occluders and backgrounds.
  • ·Integration with Unreal Engine and After Effects for production pipelines.
  • ·Scene merging and model sequence support for animations.
  • ·Automatic AprilTag detection for scene alignment without manual intervention.
  • ·Export of models to third-party viewers (paid).

In practice

Price
Freemium
Commercial use
Commercial use: yes
Available on
windows
Runs locally
Yes, 8 GB VRAM recommended
FR interface
No

Security and data

Rating
Security: nothing to flag
Your data
Data stays local
Known incidents
Export PLY passé en abonnement en 2026.
Maintenance
Active

Links and repository checked on 25 October 2026 · added on 1 June 2023

How to install Postshot (Jawset)

1. Check that your PC runs Windows 10 or later and is equipped with an NVIDIA GPU with compute capability 7.5 minimum (RTX 2060, Quadro T400/RTX 4000 or higher). 2. Go to jawset.com and click "Download for free". 3. Download the installer and verify its integrity if a checksum is provided on the page. 4. Run the installer and follow the on-screen steps. 5. On first launch, create or sign in to your Jawset account to activate your licence. 6. All processing runs locally: no images or scene data are sent to external servers.

In the same category

Whole category 3D & printing →