标签：#Cars

The Tesla Cybercab, that golden two-seater central to Elon Musk's robo-supremacist ambitions, is finally nearing it's public launch. Whether or not the no-steering wheel and no-pedal vehicle is actually ready for public roads, let alone customers, remains very much in doubt. According to The Information, Tesla is planning a public launch of the Cybercab in […]

The American automaker returns to the top category of endurance racing next year.

A bad cutout rarely announces itself as a bad cutout. The car lands on a new backdrop, the paint looks clean, then a thin piece is gone. An antenna. A tire lip. The dark seam under a rocker panel. The complaint that comes back is never technical. The vehicle looks wrong. I wanted the last correction stage to fix fuzzy edges without handing it the whole car to rewrite. That sounds like a small distinction. It stops being small the first time a model improves one boundary and quietly damages another. So the rule is physical. Edit the uncertain strip. Leave the settled area alone. This is Part 2. Part 1, "Negative Space Is a Label", was about supervision: what the pixels beside an object teach a model, and why a shadow touching a tire has to be labeled as evidence against foreground. This one moves from training to runtime. A mask already exists. Where is a learned stage allowed to act? 1. The contract lives in the band CarSegNet is the research implementation here. Its pipeline module splits the route by media type, and the docstring says the design more clearly than any diagram I could draw after the fact. Stills run SAM 3 text concept, then NSJ alpha, then composite. A detector box prompt and a depth prior are optional inputs. Video runs SAM 3.1 multiplex propagation, per-frame NSJ with temporal handling, a depth-parallax plate, composite, encode. The list matters less than the handoff. SAM gives a semantic prior. NSJ receives a trimap band. The compositor receives a matte only after the prior and the refiner have each done bounded work. flowchart TD image[Vehicle Image] segment[Concept Mask] trimap[Trimap Band] refiner[NSJ Alpha Refiner] depth[Depth Prior] composite[Showroom Composite] frozen[Prior Frozen Outside Band] image --> segment segment --> trimap trimap --> refiner image --> depth depth --> refiner refiner --> composite segment -.-> frozen frozen --> composite The diagram is a contract. It is not a model zoo. The refiner edits the uncertain strip. The sema

The Gasolini AR1 uses 2-cylinder Honda bike engine, and an EV is underway, too.

A lot of automakers talk about wanting to minimize or eliminate driver distractions so as to make the experience of driving more rewarding and safer overall. Lamborghini has a different strategy; it wants the driver to become one with their vehicle. This helps explain the storied super car maker's tagline for the new Revuelto SV: […]

Czinger used topological design and additive manufacturing to make the brakes.

Ford said today that its next-generation electric vehicle - recently dubbed Fathom - will go into production at the automaker's recently overhauled Louisville Assembly Plant in the first quarter of 2027. The first Fathoms will be prototypes, with Ford's team in Louisville already in the production-level pre-tooling phase at the recently converted facility. Factory workers […]

My drive of the 2027 Corvette Grand Sport X began under oily black clouds, a torrential weather front releasing its grip on Manhattan - an inauspicious start for any mega-powered sports car. Rain pelted the waterlogged pavement, as I set course for the mountain-man roads of the Catskills, then on to Long Island and New […]

Pricing hasn't changed, and now you can get captain's chairs for the R1S.

Rivian R1S owners, rejoice. Rivian has heard your pleas for second-row captain's chairs. For years, Rivian owners have lamented the absence of captain's chairs in the R1S, noting that the three-row SUV would be much improved with standalone seats instead of a bench in the second row. Parents groused that loading and unloading kids in […]

JCB has invested heavily in hydrogen to power its diggers and other machinery.

Jaguar's all-electric Type 01 comes with a very beige interior that divides the four seats with a "spine" that spans the length of the cabin. New photos shared by Jaguar show a low-slung driver's seat, alongside a slim dashboard with a smartphone-style display in the center. This vehicle doesn't come with a traditional rear-view mirror, […]

The deal starts with the arrival of the GEN4 car and 2026/2027 season this December.

Depending on the model, you might have hundreds to choose from—or just one.

A car mask can pass review and still teach the model to keep the wrong pixels. The outline looks clean. The bumper is inside. The wheels are inside. Then the trained network holds onto the dark patch under the tires, because the label treated that patch as part of the vehicle's visual neighborhood. Training stays quiet. Production gets loud the first time a listing photo drags a strip of the old lot onto a new backdrop. AutoLensAI turns dealer photography into listing-ready vehicle media. This installment follows the earlier pieces on segmentation and image provenance, then narrows to one question: how do I teach a matting model that the shadow touching a tire is evidence against foreground rather than a faint version of it? 1. The failure arrives without an error message Vehicle matting estimates which pixels belong to the vehicle, at finer boundary resolution than segmentation gives. Tires, rocker panels, glossy showroom floors, and the halo under a lowered front lip are where a pretty binary mask does its damage. Two cases cause most of it. A cast shadow can touch rubber and still sit outside the object. A reflection can match paint color exactly and still belong to the floor. Both look like they belong to the car in a thumbnail. Neither belongs to it in geometry. A binary target has no vocabulary for that distinction. Every pixel is in or out, so the annotator's only lever is where to put the line. Push the line outward and shadow becomes vehicle. Pull it inward and the wheel arch loses its edge. Neither answer says the thing that matters, which is that some exterior pixels are ordinary background and some are adversarial background sitting one pixel from the object. The model learns the difference anyway. It learns it wrong, because nothing in the supervision ever separated the two. 2. Three states, not two The supervision contract uses three: state meaning training treatment vehicle body, glass, wheels, trim, and visible geometry foreground loss hard negative

Ford dealers were told about the new Escape-sized model; one of them spilled the beans.

The newest Outback sticks to the script; that's no bad thing if you like Outbacks.

Ford is rolling out a new AI-powered assistant that can answer questions about your Ford or Lincoln vehicle, such as how much fuel you'll need for your next road trip or whether your truck can tow that new motor boat. The app is rolling out first to the Ford and Lincoln mobile apps, where it […]

Four weeks ago, San Francisco 49ers coach Kyle Shanahan was involved in an accident near downtown Palo Alto. At the time Shanahan said only that the accident was his fault. But during a recent press conference he shared more details about the incident, including the fact that he had his Tesla's Autopilot engaged at the […]

There's no evidence the truck will be a cheap EV truck, but what if it were?