swift webrtc modify CMSampleBuffer to apply some filter effect

i want to add some filter effect into localVideo, so i did modify CMSampleBuffer:

1. Convert to UIImage
2. Using VNFaceDetector to detect face boundingBox
3. Add my filter image into camera image
4. Convert back to CMSampleBuffer

func captureOutput(_ output: AVCaptureOutput, didOutput sampleBuffer: CMSampleBuffer, from connection: AVCaptureConnection) {
        
        guard let imageBuffer = CMSampleBufferGetImageBuffer(sampleBuffer) else {
            return
        }
        let ciimage = CIImage(cvPixelBuffer: imageBuffer)
        let image = convert(cmage: ciimage)
        print("image: \(image.size)")
        
        let faceDetectionRequest = VNDetectFaceLandmarksRequest(completionHandler: { (request: VNRequest, error: Error?) in
            DispatchQueue.main.async {[weak self] in
                if let observations = request.results as? [VNFaceObservation], !observations.isEmpty {
                    for observation in observations {
                        let box = observation.boundingBox
                        let boxFrame = CGRect(x: box.origin.x * image.size.width, y: box.origin.y * image.size.height, width: box.width * image.size.width, height: box.height * image.size.height)
                        print("box: \(boxFrame)")
                        let logo = UIImage(named: "dog_nose")!
                        if let newImage = self?.drawImageIn(image, logo, inRect: boxFrame){
                            if let pxBuffer = self?.convertImageToBuffer(from: newImage){
                                var newSampleBuffer: CMSampleBuffer? = nil
                                var timimgInfo: CMSampleTimingInfo = .invalid
                                var videoInfo: CMVideoFormatDescription? = nil
                                CMVideoFormatDescriptionCreateForImageBuffer(allocator: nil, imageBuffer: pxBuffer, formatDescriptionOut: &videoInfo)
                                if videoInfo != nil{
                                    CMSampleBufferCreateForImageBuffer(allocator: kCFAllocatorDefault, imageBuffer: pxBuffer, dataReady: true, makeDataReadyCallback: nil, refcon: nil, formatDescription: videoInfo!, sampleTiming: &timimgInfo, sampleBufferOut: &newSampleBuffer)
                                    if newSampleBuffer != nil{
                                        self?.outputCaptureDelegate?.captureOutput!(output, didOutput: newSampleBuffer!, from: connection)
                                        return
                                    }
                                }

                            }
                        }
                    }
                }
                self?.outputCaptureDelegate?.captureOutput!(output, didOutput: sampleBuffer, from: connection)
            }
        })
        let imageRequestHandler = VNImageRequestHandler(cvPixelBuffer: imageBuffer, orientation: .up, options: [:])
        do {
            try imageRequestHandler.perform([faceDetectionRequest])
        } catch {
            print(error.localizedDescription)
        }
    }

func convert(cmage: CIImage) -> UIImage {
        let context = CIContext(options: nil)
        let cgImage = context.createCGImage(cmage, from: cmage.extent)!
        let image = UIImage(cgImage: cgImage)
        return image
    }
    
    func drawImageIn(_ image: UIImage, _ logo: UIImage, inRect: CGRect) -> UIImage {
        let renderer = UIGraphicsImageRenderer(size: image.size)
        return renderer.image { context in
            image.draw(in: CGRect(origin: CGPoint.zero, size: image.size))
            logo.draw(in: inRect)
        }
    }
    
    func convertImageToBuffer(from image: UIImage) -> CVPixelBuffer? {
        let attrs = [
            String(kCVPixelBufferCGImageCompatibilityKey) : true,
            String(kCVPixelBufferCGBitmapContextCompatibilityKey) : true
        ] as [String : Any]
        var buffer : CVPixelBuffer?
        let status = CVPixelBufferCreate(kCFAllocatorDefault, Int(image.size.width), Int(image.size.height), kCVPixelFormatType_32ARGB, attrs as CFDictionary, &buffer)
        guard (status == kCVReturnSuccess) else {
            return nil
        }
        
        CVPixelBufferLockBaseAddress(buffer!, CVPixelBufferLockFlags(rawValue: 0))
        let pixelData = CVPixelBufferGetBaseAddress(buffer!)
        
        let rgbColorSpace = CGColorSpaceCreateDeviceRGB()
        let context = CGContext(data: pixelData, width: Int(image.size.width), height: Int(image.size.height), bitsPerComponent: 8, bytesPerRow: CVPixelBufferGetBytesPerRow(buffer!), space: rgbColorSpace, bitmapInfo: CGImageAlphaInfo.noneSkipFirst.rawValue)
        
        context?.translateBy(x: 0, y: image.size.height)
        context?.scaleBy(x: 1.0, y: -1.0)
        
        UIGraphicsPushContext(context!)
        image.draw(in: CGRect(x: 0, y: 0, width: image.size.width, height: image.size.height))
        UIGraphicsPopContext()
        CVPixelBufferUnlockBaseAddress(buffer!, CVPixelBufferLockFlags(rawValue: 0))
        
        return buffer
    }

but the problem is video is more slow and the image if wrong orientation, did someone faced this?