The optical array is embedded on a metasurface that, at 700~nm height, is flat and sits on the sensor cover glass at 2. 5~mm focal distance from the sensor.
We also have a better zero-shot shape-aware editing ability based on the text-to-video model.
Prior work usually requires specific guidance such as the flickering frequency, manual annotations, or extra consistent videos to remove the flicker.
Without introducing any external supervision and human priors, the proposed FPR effectively suppresses wrong activations from the background objects.
Self-supervised representation learning follows a paradigm of withholding some part of the data and tasking the network to predict it from the remaining part.
We present a high-fidelity 3D generative adversarial network (GAN) inversion framework that can synthesize photo-realistic novel views while preserving specific details of the input image.
We propose a simple yet effective reflection-free cue for robust reflection removal from a pair of flash and ambient (no-flash) images.
A progressive propagation strategy with pseudo labels is also proposed to enhance DVP's performance on video propagation.
We present a new data-driven approach with physics-based priors to scene-level normal estimation from a single polarization image.
Due to the lack of a large-scale reflection removal dataset with diverse real-world scenes, many existing reflection removal methods are trained on synthetic data plus a small amount of real-world data, which makes it difficult to evaluate the strengths or weaknesses of different reflection removal methods thoroughly.
Extensive quantitative and perceptual experiments show that our approach obtains superior performance than state-of-the-art methods on blind video temporal consistency.
We present a novel formulation to removing reflection from polarized images in the wild.
Our flow-to-depth layer is differentiable, and thus we can refine camera poses by maximizing the aggregated confidence in the camera pose refinement module.