According to Isaac Reynolds, Pixel Camera Product Manager, Best Take is not only great for creating the perfect group shot, but also for having some fun. “Making a so-called ‘worst take’ with funny expressions all around is my favorite use case. You have to choose which of your ridiculous expressions is the best yourself, and it’s pretty funny to see what you can create!,” Reynolds said.
The idea for Best Take originated during a week-long summit involving teams from Google Photos, Pixel, and Google Research. This summit aimed to address the “group shot dilemma,” a challenge identified through user research. The teams brainstormed on how to help and ultimately came up with the concept of an AI-powered tool that merges different facial expressions from multiple pictures into a single image.
Initial concept testing revealed that the feature appealed to users, in part because it aligned with common behavior. People already take multiple photos when capturing group shots. Lillian Chen, Photos Product Manager, noted, “A big reason this feature resonates with people is that the composite image feels true to their memory — by drawing from pictures taken in quick succession, it’s essentially the same moment. The feature balances authenticity with helpfulness to solve a real pain point.”
Best Take operates through a blend of diverse AI models that analyze images, check timestamps to locate photos taken in sequence, and seek out signals such as head poses and facial expressions. These models then suggest images of faces where subjects are looking at the lens and smiling. Once selected, technology adapted from AI-driven Google Photos features like Magic Eraser and Cinematic photos seamlessly blends the images and corrects any background errors.
In addition to providing an automatic suggestion, the design also prioritizes user choice. Navin Sarma, Research Product Manager, stated, “Our goal is to give users control over their memories, including which alternative expression they prefer. Even the most subtle differences can matter to each person in the photo.”
