Picsart Video Background Removal API vs Robust Video Matting

Picsart Video Background Removal API removes video backgrounds or replaces them with a custom color or image. It accepts WEBM, MP4, and MOV files up to 500 MB and 1920×1080 resolution. Requests can specify a background color or image URL; transparent output is available but requires WebM. Processing is asynchronous: submit a request, receive a transaction identifier, and use that identifier to retrieve the result. Batch processing is supported. Requests require an API key in the X-Picsart-API-Key header, and accounts can make up to 500 requests per minute before excess calls receive a 429 response. Picsart lists video background removal at 15 credits per minute, with monthly credit pricing tailored to estimated volume and use case. New accounts receive 5 free credits, and a free trial provides full API access without a stated duration. The service is aimed at developers and business workflows such as e-commerce, social media, and digital asset management.

Robust Video Matting is a free project for separating people from video backgrounds. It processes frames with a recurrent neural network that carries temporal memory, and the project says it can perform matting in real time without additional inputs. A browser webcam demo runs the model live and can visualize its recurrent states. The conversion API accepts a video or image sequence and can produce a composited video or PNG sequence, optionally including alpha and foreground outputs.

Models are available for PyTorch, TorchHub, TorchScript, ONNX, TensorFlow, TensorFlow.js, and CoreML. MobileNetv3 is recommended for most uses; ResNet50 is larger and described as offering small performance improvements. The README reports GPU throughput figures, including 4K at 76 FPS and HD at 104 FPS on a GTX 1080 Ti, and 4K at 154 FPS and HD at 172 FPS on an RTX 3090 with FP16 under specified settings. The project cautions that file conversion runs much slower because its script does not use hardware video encoding or decoding or parallel tensor transfers. CoreML models require iOS 13 or later and do not support dynamic resolution. The code is GPL-3.0 licensed.