Non-line-of-sight imaging employs ultra-fast illumination and sensing devices to reconstruct scenes outside their line of sight by analyzing the temporal profile of indirect scattered illumination on a secondary relay surface. Commonly, the NLOS methods transform the temporal domain into the frequency domain and operate on it, and then identify surface locations by locating the maxima in amplitude along the reconstruction volume. Phase information, which is virtual as it results from a Fourier transform, is very often discarded or ignored. We incorporate phase information into our novel Zero-Phase Phasor Fields imaging technique, which we derive for a confocal capture configuration. We show how, at positions that belong to the hidden geometry, we can ensure the phase is zero, so we can locate the hidden geometry with great precision by locating the zero crossings in the phase. This allows us to reconstruct at widely spaced locations and still achieve up to 125 micrometer depth precision, as our experimental validation shows with both synthetic and captured data, the latter publicly available. Moreover, the phase is robust to noise, as we demonstrate with decreasing signal-to-noise ratio using publicly available dataset captures of the same scene.
Shape from shading using a single image of a Lambertian surface is inherently ambiguous. When the light source direction is known, the surface normal estimation has a cone-ambiguity, which worsens when the source is unknown. Recently, shape from heat conduction has emerged as an approach that leverages heat transport equations to estimate the Shape Laplacian operator, an intrinsic measure of shape. However, deriving surface normals from the Laplacian operator encounters a local binary convex/concave ambiguity. Our contribution introduces a novel theory to resolve these local shape ambiguities (excluding a few degeneracies) without relying on priors like smoothness, by combining the cues from shading and heat conduction. Our method ensures the mathematical constraints of both shading and the Laplacian are satisfied simultaneously, even with an unknown light source. We validate our theory through simulations of complex shapes and analyze its performance in the presence of noise.
Holographic displays are plagued by speckle D noise-like artifacts caused by the coherent interference of laser light. To mitigate this challenge, state-of-the-art systems use time multiplexing on fast spatial light modulators (SLMs) to effectively temporally smooth out these effects. In our work, we observe that such an approach struggles in practice in the context of dynamic content, manifesting motion blur and stroboscopic artifacts thanks to a fundamental mismatch between expected and displayed motion. To tackle this challenge, we propose a paradigm of holographic high-speed display, where we use the underlying fast SLM to reproduce target content that changes at the same framerate. Approaches built using this paradigm mitigate motion blur and strobing, and simultaneously minimize speckle and maximize contrast with the right loss functions. We demonstrate such a methodology in both simulation and a real system.
Many consumer cameras are equipped with 8-bit image sensors, which often struggle to capture scenes with a High Dynamic Range (HDR). This limitation can result in overexposed or underexposed regions, a loss of fine details due to low bit-depth compression, skewed color distributions, and noticeable noise in dark areas. Traditional Standard Dynamic Range (SDR) image enhancement methods typically focus on color mapping by expanding the color range and adjusting brightness. However, they often fail to restore details in dynamic range extremes, i.e. regions where pixel values approach the minimum or maximum limits. We define "exposure-limited image enhancement" as the process of enhancing images with large missing areas due to exposure issues within the SDR space, which differs from existing degrees mis-exposed image enhancement degrees methods primarily aimed at correcting color distributions. To enhance these exposure-limited images and overcome the limitations of current models, we propose a novel two-stage approach. In the first stage, we remap color and brightness to a suitable range while preserving existing details. In the second stage, we use a diffusion prior to generate content in severely overexposed or underexposed regions, which are otherwise lost during capture. Notably, this generative refinement module can also serve as a plug-and-play component alongside existing enhancement methods. Extensive experiments demonstrate that our method significantly improves image quality and detail, outperforming state-of-the-art techniques in dynamic range extremes. The project page is at https://Sagiri0208.github.io.
Holographic displays are gaining increasing popularity, particularly as a holy grail solution to augmented and virtual reality (AR/VR) wearable displays. However, the generation of holograms is computationally intensive for AR/VR edge devices, which are expected to be compact and lightweight with low power consumption and heat dissipation to last all day. To address this, we propose a distributed hologram generation framework, dubbed HoloZip, to jointly generate, compress, transmit, and decode computer-generated holograms across the cloud-edge devices. Specifically, we perform compute intensive hologram generation via a vision transformer based backbone on the cloud, compress and transmit before decoding on a local edge device by a lightweight model. Our HoloZip framework supports both both 2D/3D holograms as well as holographic videos, achieving a reconstruction quality of over 30 dB in PSNR (lossy compression standard) with bit rates as low as 0.6 bits per pixel as validated by experiments.
