New imaging software converts single compatible camera photographs into realistic 3D images and models, removing the need for specialised capture equipment and viewing devices altogether.
Canon has launched Dual Pixel 3D, a new imaging technology that works with the Dual Pixel 3D Converter application to create three-dimensional images and models from a single photograph. The Windows-based software uses depth and phase-detection information captured through compatible EOS R-series cameras, eliminating the need for specialised 3D cameras, multi-camera rigs, or dedicated viewing equipment.
The technology uses Canon’s Dual Pixel CMOS AF architecture, in which each pixel incorporates two photodiodes that can be read independently. The slight difference between the views captured by these photodiodes provides depth information that the software can process to reconstruct the subject in three dimensions.
Users can import compatible Dual Pixel RAW images, while selected cameras can also provide JPEG files containing depth information. The application then processes this information using Canon’s proprietary algorithms to generate 3D content while retaining photographic textures and colour information. The resulting models can be exported in OBJ or GLB formats, while MP4 output is also supported for video-based presentations.
The software provides controls for adjusting the perceived depth of the generated model. Users can increase the effect for a stronger three-dimensional appearance or reduce it for a flatter presentation. Backgrounds can also be isolated, removed, or replaced before export.
Canon says the technology can support applications including product presentation, websites, presentations, creative content, and other workflows requiring three-dimensional visualisation. Compatible cameras include models such as the EOS R5 Mark II, EOS R5, EOS R6 Mark III, EOS R6 Mark II, EOS R7, EOS R8 Mark II, EOS R8, and EOS R10, with supported lenses also required.
