태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
3D Car Instance Understanding is the task of estimating properties (e.g.translation, rotation and shape) of a moving or parked vehicle on the road.
<span style="color:grey; opacity: 0.6">( Image credit: Occlusion-Net )</span>
출처에 같은 태스크 이름으로 연결된 데이터셋입니다. 동명 태스크가 포함될 수 있으므로, 비교할 때는 평가 결과의 조건도 확인하세요.
ApolloCar3DT is a dataset that contains 5,277 driving images and over 60K car instances, where each car is fitted with an industry-grade 3D CAD model with absolute model size and semantically labelled keypoints. This dataset is above 20 times larger than PASCAL3D+ and KITTI, the current state-of-the-art. Source: ApolloCar3D: A Large 3D Car Instance Understanding Benchmark for Autonomous Driving Image Source: http://apolloscape.auto/car_instance.html
We provide manual annotations of 14 semantic keypoints for 100,000 car instances (sedan, suv, bus, and truck) from 53,000 images captured from 18 moving cameras at Multiple intersections in Pittsburgh, PA. Please fill the google form to get a email with the download links:
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.