arXiv subjects

Min H. Kim

Publications and source records attributed to Min H. Kim.

27 records · Page 2Linked to original sources

arXiv2022

Differentiable Transient Rendering

Recent differentiable rendering techniques have become key tools to tackle many inverse problems in graphics and vision. Existing models, however, assume steady-state light transport, i.e., infinite speed of light. While this is a safe assumption for many applications, recent advances in ultrafast imaging leverage the wealth of information that can be extracted from the exact time of flight of light. In this context, physically-based transient rendering allows to efficiently simulate and analyze light transport considering that the speed of light is indeed finite. In this paper, we introduce a novel differentiable transient rendering framework, to help bring the potential of differentiable approaches into the transient regime. To differentiate the transient path integral we need to take into account that scattering events at path vertices are no longer independent; instead, tracking the time of flight of light requires treating such scattering events at path vertices jointly as a multidimensional, evolving manifold. We thus turn to the generalized transport theorem, and introduce a novel correlated importance term, which links the time-integrated contribution of a path to its light throughput, and allows us to handle discontinuities in the light and sensor functions. Last, we present results in several challenging scenarios where the time of flight of light plays an important role such as optimizing indices of refraction, non-line-of-sight tracking with nonplanar relay walls, and non-line-of-sight tracking around two corners.

cs.GR↗

arXiv2021

Single-shot Hyperspectral-Depth Imaging with Learned Diffractive Optics

Imaging depth and spectrum have been extensively studied in isolation from each other for decades. Recently, hyperspectral-depth (HS-D) imaging emerges to capture both information simultaneously by combining two different imaging systems; one for depth, the other for spectrum. While being accurate, this combinational approach induces increased form factor, cost, capture time, and alignment/registration problems. In this work, departing from the combinational principle, we propose a compact single-shot monocular HS-D imaging method. Our method uses a diffractive optical element (DOE), the point spread function of which changes with respect to both depth and spectrum. This enables us to reconstruct spectrum and depth from a single captured image. To this end, we develop a differentiable simulator and a neural-network-based reconstruction that are jointly optimized via automatic differentiation. To facilitate learning the DOE, we present a first HS-D dataset by building a benchtop HS-D imager that acquires high-quality ground truth. We evaluate our method with synthetic and real experiments by building an experimental prototype and achieve state-of-the-art HS-D imaging results.

eess.IV↗

arXiv2021

Edge-aware Bidirectional Diffusion for Dense Depth Estimation from Light Fields

We present an algorithm to estimate fast and accurate depth maps from light fields via a sparse set of depth edges and gradients. Our proposed approach is based around the idea that true depth edges are more sensitive than texture edges to local constraints, and so they can be reliably disambiguated through a bidirectional diffusion process. First, we use epipolar-plane images to estimate sub-pixel disparity at a sparse set of pixels. To find sparse points efficiently, we propose an entropy-based refinement approach to a line estimate from a limited set of oriented filter banks. Next, to estimate the diffusion direction away from sparse points, we optimize constraints at these points via our bidirectional diffusion method. This resolves the ambiguity of which surface the edge belongs to and reliably separates depth from texture edges, allowing us to diffuse the sparse set in a depth-edge and occlusion-aware manner to obtain accurate dense depth maps.

cs.CV↗

arXiv2021

Differentiable Diffusion for Dense Depth Estimation from Multi-view Images

We present a method to estimate dense depth by optimizing a sparse set of points such that their diffusion into a depth map minimizes a multi-view reprojection error from RGB supervision. We optimize point positions, depths, and weights with respect to the loss by differential splatting that models points as Gaussians with analytic transmittance. Further, we develop an efficient optimization routine that can simultaneously optimize the 50k+ points required for complex scene reconstruction. We validate our routine using ground truth data and show high reconstruction quality. Then, we apply this to light field and wider baseline images via self supervision, and show improvements in both average and outlier error for depth maps diffused from inaccurate sparse points. Finally, we compare qualitative and quantitative results to image processing and deep learning methods. http://visual.cs.brown.edu/diffdiffdepth

cs.CV↗

arXiv2020

View-consistent 4D Light Field Depth Estimation

We propose a method to compute depth maps for every sub-aperture image in a light field in a view consistent way. Previous light field depth estimation methods typically estimate a depth map only for the central sub-aperture view, and struggle with view consistent estimation. Our method precisely defines depth edges via EPIs, then we diffuse these edges spatially within the central view. These depth estimates are then propagated to all other views in an occlusion-aware way. Finally, disoccluded regions are completed by diffusion in EPI space. Our method runs efficiently with respect to both other classical and deep learning-based approaches, and achieves competitive quantitative metrics and qualitative performance on both synthetic and real-world light fields

cs.CV↗

arXiv2019

Extreme View Synthesis

We present Extreme View Synthesis, a solution for novel view extrapolation that works even when the number of input images is small--as few as two. In this context, occlusions and depth uncertainty are two of the most pressing issues, and worsen as the degree of extrapolation increases. We follow the traditional paradigm of performing depth-based warping and refinement, with a few key improvements. First, we estimate a depth probability volume, rather than just a single depth value for each pixel of the novel view. This allows us to leverage depth uncertainty in challenging regions, such as depth discontinuities. After using it to get an initial estimate of the novel view, we explicitly combine learned image priors and the depth uncertainty to synthesize a refined image with less artifacts. Our method is the first to show visually pleasing results for baseline magnifications of up to 30X.

cs.CV↗

arXiv2018

DeepToF: Off-the-Shelf Real-Time Correction of Multipath Interference in Time-of-Flight Imaging

Time-of-flight (ToF) imaging has become a widespread technique for depth estimation, allowing affordable off-the-shelf cameras to provide depth maps in real time. However, multipath interference (MPI) resulting from indirect illumination significantly degrades the captured depth. Most previous works have tried to solve this problem by means of complex hardware modifications or costly computations. In this work we avoid these approaches, and propose a new technique that corrects errors in depth caused by MPI that requires no camera modifications, and corrects depth in just 10 milliseconds per frame. By observing that most MPI information can be expressed as a function of the captured depth, we pose MPI removal as a convolutional approach, and model it using a convolutional neural network. In particular, given that the input and output data present similar structure, we base our network in an autoencoder, which we train in two stages: first, we use the encoder (convolution filters) to learn a suitable basis to represent corrupted range images; then, we train the decoder (deconvolution filters) to correct depth from the learned basis from synthetically generated scenes. This approach allows us to tackle the lack of reference data, by using a large-scale captured training set with corrupted depth to train the encoder, and a smaller synthetic training set with ground truth depth to train the corrector stage of the network, which we generate by using a physically-based, time-resolved rendering. We demonstrate and validate our method on both synthetic and real complex scenarios, using an off-the-shelf ToF camera, and with only the captured incorrect depth as input.

cs.GR↗

arXiv2006

Circular polarization memory effect in enhanced backscattering of light under partially coherent illumination

We experimentally study the propagation of circularly polarized light in the sub-diffusion regime by exploiting enhanced backscattering (EBS, also known as coherent backscattering) of light under low spatial coherence illumination. We demonstrate for the first time that circular polarization memory effect exists in EBS over a large range of scatterers' sizes in this regime. We show that EBS measurements under low spatial coherence illumination from the helicity preserving and orthogonal helicity channels cross over as the mean free pathlength of light in media varies, and that the cross point indicates the transition from multiple to double scattering in EBS of light.

cond-mat.mes-hall↗

arXiv2006

Probing minimal scattering events in enhanced backscattering of light using low-coherence induced dephasing

We exploit low spatial coherence illumination to dephase time-reversed partial waves outside its finite coherence area, which virtually creates a controllable coherence volume and isolates the minimal number of scattering events from higher order scattering in enhanced backscattering (EBS, also known as coherent backscattering) of light. We report the first experimental evidence that the minimum number of scattering events in EBS is double scattering in discrete random media, which has been hypothesized since the first observation of EBS of light. We discuss several unique characteristics and potential applications of low-coherence EBS in weakly scattering random media.

cond-mat.mes-hall↗