Move Lights in a Photograph in 3D
CVPR Highlight paper from Yale and Adobe, but it's research not a product.

Photo-based quotes beat manual surveys using Gemini vision and cube-sheet volumes.
UK house removal companies and their customers
Movebot · SurveySparrow · Fohr
My colleague experienced this first-hand recently, hence why we build this tool. Instead of manually filling out a form, you just photo the rooms in your house. It identifies the objects, then uses industry standard "cube-sheets" (inventory lists), which have volume & weights of common items, to calculate the vehicle size required and generate the quote.
This reduces hours / days of waiting for a quote to a 5 minute walk around your house with your phone and completely removes the need to manually enter items.
I am looking for feedback from anyone who has moved house/office recently and whether this would have been a benefit and any other feature ideas?
This is just a demo, but we already have additional potential features: specify fragile items, specify disassembly.
CVPR Highlight paper from Yale and Adobe, but it's research not a product.
Academic CVPR research that moves 3D lighting in photos when Photoshop can't.
LiDAR + RT60 physics for meeting rooms, but AV consultants already solve this.
Computer vision repurposed to visualize nostalgia and entropy instead of faces and objects.
Nice idea but no evidence of working product or user traction.
Instead of warping text or asking image questions, this prototype makes the solution letters share a geometric motion signature while decoys move differently — you must watch temporal patterns to solve it. The GIFs and client-side demo make the idea immediately tangible, but it's clearly a proof‑of‑concept: the solution is exposed in memory (no server-side validation) and motion-based challenges create accessibility concerns.