3D Gaussian Splatting (3DGS) has recently enabled real-time rendering of unbounded 3D scenes for novel view synthesis. However, this technique requires dense training views to accurately reconstruct 3D geometry. A limited number of input views will significantly degrade reconstruction quality, resulting in artifacts such as “floaters” and “background collapse” at unseen viewpoints. In this work, we introduce SparseGS, an efficient training pipeline designed to address the limitations of 3DGS in scenarios with sparse training views. SparseGS incorporates depth priors, novel depth rendering techniques, and a pruning heuristic to mitigate floater artifacts, alongside an Unseen Viewpoint Regularization module to alleviate background collapses. Our extensive evaluations on the Mip-NeRF360, LLFF, and DTU datasets demonstrate that SparseGS achieves highquality reconstruction in both unbounded and forwardfacing scenarios, with as few as 12 and 3 input images, respectively, while maintaining fast training and real-time rendering capabilities.

Recent advancements in 2D and multimodal models have achieved remarkable success by leveraging large-scale training on extensive datasets. However, extending these achievements to enable free-form interactions and high-level semantic operations with complex 3D/4D scenes remains challenging. This difficulty stems from the limited availability of large-scale, annotated 3D/4D or multi-view datasets, which are crucial for generalizable vision and language tasks such as open-vocabulary and prompt-based segmentation, language-guided editing, and visual question answering (VQA). In this paper, we introduce Feature4X, a universal framework designed to extend any functionality from 2D vision foundation model into the 4D realm, using only monocular video input, which is widely available from user-generated content. The "X" in Feature4X represents its versatility, enabling any task through adaptable, model-conditioned 4D feature field distillation. At the core of our framework is a dynamic optimization strategy that unifies multiple model capabilities into a single representation. Additionally, to the best of our knowledge, Feature4X is the first method to distill and lift the features of video foundation models (e.g. SAM2, InternVideo2) into an explicit 4D feature field using Gaussian Splatting. Our experiments showcase novel view segment anything, geometric and appearance scene editing, and free-form VQA across all time steps, empowered by LLMs in feedback loops. These advancements broaden the scope of agentic AI applications by providing a foundation for scalable, contextually and spatiotemporally aware systems capable of immersive dynamic 4D scene interaction.

Vision language models (VLMs) have shown remarkable capabilities in integrating linguistic and visual reasoning but remain fundamentally limited in understanding dynamic spatiotemporal interactions. Humans effortlessly track and reason about object movements, rotations, and perspective shifts-abilities essential for robust dynamic real-world understanding yet notably lacking in current VLMs. In this paper, we introduce VLM4D, the first benchmark specifically designed to evaluate the spatiotemporal reasoning capabilities of VLMs. Our benchmark comprises diverse real-world and synthetic videos accompanied by carefully curated question-answer pairs emphasizing translational and rotational motions, perspective awareness, and motion continuity. Through comprehensive evaluations of state-of-the-art open and closed-source VLMs, we identify significant performance gaps compared to human baselines, highlighting fundamental deficiencies in existing models. Extensive analysis reveals that VLMs struggle particularly with integrating multiple visual cues and maintaining temporal coherence. We further explore promising directions, such as leveraging 4D feature field reconstruction and targeted spatiotemporal supervised fine-tuning, demonstrating their effectiveness in enhancing spatiotemporal comprehension. Our work aims to encourage deeper exploration into improving VLMs' spatial and temporal grounding, paving the way towards more capable and reliable visual intelligence for dynamic environments.

The blooming of virtual reality and augmented reality (VR/AR) technologies has driven an increasing demand for the creation of high-quality, immersive, and dynamic environments. However, existing generative techniques either focus solely on dynamic objects or perform outpainting from a single perspective image, failing to meet the requirements of VR/AR applications that need free-viewpoint, 360$^{\circ}$ virtual views where users can move in all directions. In this work, we tackle the challenging task of elevating a single panorama to an immersive 4D experience. For the first time, we demonstrate the capability to generate omnidirectional dynamic scenes with 360$^{\circ}$ views at 4K (4096 $\times$ 2048) resolution, thereby providing an immersive user experience. Our method introduces a pipeline that facilitates natural scene animations and optimizes a set of 3D Gaussians using efficient splatting techniques for real-time exploration. To overcome the lack of scene-scale annotated 4D data and models, especially in panoramic formats, we propose a novel Panoramic Denoiser that adapts generic 2D diffusion priors to animate consistently in 360$^{\circ}$ images, transforming them into panoramic videos with dynamic scenes at targeted regions. Subsequently, we propose Dynamic Panoramic Lifting to elevate the panoramic video into a 4D immersive environment while preserving spatial and temporal consistency. By transferring prior knowledge from 2D models in the perspective domain to the panoramic domain and the 4D lifting with spatial appearance and geometry regularization, we achieve high-quality Panorama-to-4D generation at a resolution of 4K for the first time. Project page: https://4k4dgen.github.io/.

Generative diffusion models can serve as priors, ensuring that image restoration solutions adhere to natural image manifolds. For facial images, however, personalized priors are essential to accurately reconstruct individual-specific facial features. We propose Dual-Pivot Tuning - a simple yet effective two-stage approach to personalize blind restoration systems while preserving general prior integrity. Our key observation is that for efficient personalization, the diffusion model should be tuned around a fixed textual pivot in the first step, while in the second step a guiding network should be tuned in a generic (non-personalized) manner, using the personalized diffusion model as a fixed "pivot". This approach ensures that personalization does not interfere with the restoration process, producing results with a natural appearance that show high fidelity to both identity and degraded image attributes. We conducted extensive experiments with images of widely recognized individuals, evaluating our approach both qualitatively and quantitatively against relevant baselines. Notably, our personalized prior not only achieves superior identity fidelity, but also outperforms state-of-the-art generic priors in terms of overall image quality. Project webpage is https://personalized-restoration.github.io/ and code is available at https://github.com/personalized-restoration/personalized-restoration.

3D scene representations have gained immense popularity in recent years. Methods that use Neural Radiance fields are versatile for traditional tasks such as novel view synthesis. In recent times, some work has emerged that aims to extend the functionality of NeRF beyond view synthesis, for semantically aware tasks such as editing and segmentation using 3D feature field distillation from 2D foundation models. However, these methods have two major limitations: (a) they are limited by the rendering speed of NeRF pipelines, and (b) implicitly represented feature fields suffer from continuity artifacts reducing feature quality. Recently, 3D Gaussian Splatting has shown state-of-the-art performance on real-time radiance field rendering. In this work, we go one step further: in addition to radiance field rendering, we enable 3D Gaussian splatting on arbitrary-dimension semantic features via 2D foundation model distillation. This translation is not straightforward: naively incorporating feature fields in the 3DGS framework encounters significant challenges, notably the disparities in spatial resolution and channel consistency between RGB images and feature maps. We propose architectural and training changes to efficiently avert this problem. Our proposed method is general, and our experiments showcase novel view semantic segmentation, language-guided editing and segment anything through learning feature fields from state-of-the-art 2D foundation models such as SAM and CLIP-LSeg. Across experiments, our distillation method is able to provide comparable or better results, while being significantly faster to both train and render. Additionally, to the best of our knowledge, we are the first method to enable point and bounding-box prompting for radiance field manipulation, by leveraging the SAM model. Project website at: https://feature-3dgs.github.io/.

We propose a method for depth estimation under different illumination conditions, i.e., day and night time. As photometry is uninformative in regions under low-illumination, we tackle the problem through a multi-sensor fusion approach, where we take as input an additional synchronized sparse point cloud (i.e., from a LiDAR) projected onto the image plane as a sparse depth map, along with a camera image. The crux of our method lies in the use of the abundantly available synthetic data to first approximate the 3D scene structure by learning a mapping from sparse to (coarse) dense depth maps along with their predictive uncertainty – we term this, SpaDe. In poorly illuminated regions where photometric intensities do not afford the inference of local shape, the coarse approximation of scene depth serves as a prior; the uncertainty map is then used with the image to guide refinement through an uncertainty-driven residual learning (URL) scheme. The resulting depth completion network leverages complementary strengths from both modalities – depth is sparse but insensitive to illumination and in metric scale, and image is dense but sensitive with scale ambiguity. SpaDe can be used in a plug-and-play fashion, which allows for 24% improvement when augmented onto existing methods to preprocess sparse depth. We demonstrate URL on the nuScenes dataset where we improve over all baselines by an average 12.39% in all-day scenarios, 12.02% when tested specifically for daytime, and 14.95% for nighttime scenes. Code available at : https://github.com/ezhovv/all-day-depth

Reconstructing and understanding 3D structures from a limited number of images is a classical problem in computer vision. Traditional approaches typically decompose this task into multiple subtasks, involving several stages of complex mappings between different data representations. For example, dense reconstruction using Structure-from-Motion (SfM) requires transforming images into key points, optimizing camera parameters, and estimating structures. Following this, accurate sparse reconstructions are necessary for further dense modeling, which is then input into task-specific neural networks. This multi-stage paradigm leads to significant processing times and engineering complexity. In this work, we introduce the Large Spatial Model (LSM), which directly processes unposed RGB images into semantic radiance fields. LSM simultaneously estimates geometry, appearance, and semantics in a single feed-forward pass and can synthesize versatile label maps by interacting through language at novel views. Built on a general Transformer-based framework, LSM predicts global geometry via pixel-aligned point maps. To improve spatial attribute regression, we adopt local context aggregation with multi-scale fusion, enhancing the accuracy of fine local details. To address the scarcity of labeled 3D semantic data and enable natural language-driven scene manipulation, we incorporate a pre-trained 2D language-based segmentation model into a 3D-consistent semantic feature field. An efficient decoder parameterizes a set of semantic anisotropic Gaussians, allowing supervised end-to-end learning. Comprehensive experiments on various tasks demonstrate that LSM unifies multiple 3D vision tasks directly from unposed images, achieving real-time semantic 3D reconstruction for the first time.

Neural scene representations have achieved great success in parameterizing and reconstructing images, but current state of the art models are not optimized with the preservation of physical quantities in mind. While current architectures can reconstruct color images correctly, they create artifacts when trying to fit maps of polar quantities. We propose polarimetric coordinate networks (pCON), a new model architecture for neural scene representations aimed at preserving polarimetric information while accurately parameterizing the scene. Our model removes artifacts created by current coordinate network architectures when reconstructing three polarimetric quantities of interest. All code and data can be found at this link: http5://visual.ee.ucla.edu/pcon.htm.

We present a method for inferring dense depth from a camera image and a sparse noisy radar point cloud. We first describe the mechanics behind mmWave radar point cloud formation and the challenges that it poses, i.e. ambiguous elevation and noisy depth and azimuth components that yields incorrect positions when projected onto the image, and how existing works have overlooked these nuances in camera-radar fusion. Our approach is motivated by these mechanics, leading to the design of a network that maps each radar point to the possible surfaces that it may project onto in the image plane. Unlike existing works, we do not process the raw radar point cloud as an erroneous depth map, but query each raw point independently to associate it with likely pixels in the image – yielding a semi-dense radar depth map. To fuse radar depth with an image, we propose a gated fusion scheme that accounts for the confidence scores of the correspondence so that we selectively combine radar and camera embeddings to yield a dense depth map. We test our method on the NuScenes benchmark and show a 10.3% improvement in mean absolute error and a 9.1% improvement in root-mean-square error over the best method. Code: https://github.com/nesl/radar-camera-fusion-depth.

This work introduces alternating latent topologies (ALTO) for high-fidelity reconstruction of implicit 3D surfaces from noisy point clouds. Previous work identifies that the spatial arrangement of latent encodings is important to recover detail. One school of thought is to encode a latent vector for each point (point latents). Another school of thought is to project point latents into a grid (grid latents) which could be a voxel grid or triplane grid. Each school of thought has tradeoffs. Grid latents are coarse and lose high-frequency detail. In contrast, point latents preserve detail. However, point latents are more difficult to decode into a surface, and quality and runtime suffer. In this paper, we propose ALTO to sequentially alternate between geometric representations, before converging to an easy-to-decode latent. We find that this preserves spatial expressiveness and makes decoding lightweight. We validate ALTO on implicit 3D recovery and observe not only a performance improvement over the state-of-the-art, but a runtime improvement of$3-10\times$. Project website at https://visual.ee.ucla.edu/alto.htm/.

Today single image deweathering is arguably more sensitive to the dataset type, rather than the model. We introduce WeatherStream, an automatic pipeline capturing all real-world weather effects (rain, snow, and rain fog degradations), along with their clean image pairs. Previous state-of-the-art methods that have attempted the all-weather removal task train on synthetic pairs, and are thus limited by the Sim2Real domain gap. Recent work has attempted to manually collect time multiplexed pairs, but the use of human labor limits the scale of such a dataset. We introduce a pipeline that uses the power of light-transport physics and a model trained on a small, initial seed dataset to reject approximately 99.6% of unwanted scenes. The pipeline is able to generalize to new scenes and degradations that can, in turn, be used to train existing models just like fully human-labeled data. Training on a dataset collected through this procedure leads to significant improvements on multiple existing weather removal methods on a carefully human-collected test set of real-world weather effects. The dataset and code can be found in the following website: http://visual.ee.ucla.edu/wstream.htm/.

While perspective is a well-studied topic in art, it is generally taken for granted in images. However, for the recent wave of high-quality image synthesis methods such as latent diffusion models, perspective accuracy is not an explicit requirement. Since these methods are capable of outputting a wide gamut of possible images, it is difficult for these synthesized images to adhere to the principles of linear perspective. We introduce a novel geometric constraint in the training process of generative models to enforce perspective accuracy. We show that outputs of models trained with this constraint both appear more realistic and improve performance of downstream models trained on generated images. Subjective human trials show that images generated with latent diffusion models trained with our constraint are preferred over images from the Stable Diffusion V2 model 70% of the time. SOTA monocular depth estimation models such as DPT and PixelFormer, fine-tuned on our images, outperform the original models trained on real images by up to 7.03% in RMSE and 19.3% in SqRel on the KITTI test set for zero-shot transfer.

Accelerated by telemedicine, advances in Remote Photoplethysmography (rPPG) are beginning to offer a viable path toward non-contact physiological measurement. Unfortunately, the datasets for rPPG are limited as they require videos of the human face paired with ground-truth, synchronized heart rate data from a medical-grade health monitor. Also troubling is that the datasets are not inclusive of diverse populations, i.e., current real rPPG facial video datasets are imbalanced in terms of races or skin tones, leading to accuracy disparities on different demographic groups. This paper proposes a scalable biophysical learning based method to generate physio-realistic synthetic rPPG videos given any reference image and target rPPG signal and shows that it could further improve the state-of-the-art physiological measurement and reduce the bias among different groups. We also collect the largest rPPG dataset of its kind (UCLA-rPPG) with a diverse presence of subject skin tones, in the hope that this could serve as a benchmark dataset for different skin tones in this area and ensure that advances of the technique can benefit all people for healthcare equity. The dataset is available at https://visual.ee.ucla.edu/rppg_avatars.htm/.

Data-driven remote vital sign estimation provides an efficient alternative to on-site clinical monitoring, however, its performance can be biased due to the imbalanced training sets. In this work, we take remote photoplethysmography (rPPG) as an example to examine the performance bias from skin tone variations in non-contact heart rate estimation. In rPPG, recent deep learning models have significantly improved the accuracy of the physiological measurement, however, the existing datasets MMSE-HR, AFRL, and UBFC-RPPG only contain roughly 10%, 0%, and 5% of dark-skinned subjects respectively. The imbalanced training sets result in a poor generalization capability of these models and lead to unwanted bias toward different demographic groups. In Western academia, it is regrettably difficult in a university setting to collect data on these dark-skinned subjects. Here we show a first attempt to overcome the lack of dark-skinned subjects by synthetic augmentation. A joint optimization framework is utilized to translate real videos from light-skinned subjects to dark skin tones while retaining their pulsatile signals. In the experiment, our method exhibits around 38% reduction in mean absolute error for the dark-skinned group and 49% improvement on bias mitigation, as compared with the previous work trained with just real samples. Project website: https://visual.ee.ucla.edu/rppg_augmentation.htm/.

Force sensing has been a key enabling technology for a wide range of interfaces such as digitally enhanced body and world surfaces for touch interactions. Additionally, force often contains rich contextual information about user activities and can be used to enhance machine perception for improved user and environment awareness. To sense force, conventional approaches rely on contact sensors made of pressure-sensitive materials such as piezo films/discs or force-sensitive resistors. We present ForceSight, a non-contact force sensing approach using laser speckle imaging. Our key observation is that object surfaces deform in the presence of force. This deformation, though very minute, manifests as observable and discernible laser speckle shifts, which we leverage to sense the applied force. This non-contact force-sensing capability opens up new opportunities for rich interactions and can be used to power user-/environment-aware interfaces. We first built and verified the model of laser speckle shift with surface deformations. To investigate the feasibility of our approach, we conducted studies on metal, plastic, wood, along with a wide variety of materials. Additionally, we included supplementary tests to fully tease out the performance of our approach. Finally, we demonstrated the applicability of ForceSight with several demonstrative example applications.

With the resurgence of non-contact vital sign sensing due to the COVID-19 pandemic, remote heart-rate monitoring has gained significant prominence. Many existing methods use cameras; however previous work shows a performance loss for darker skin tones. In this paper, we show through light transport analysis that the camera modality is fundamentally biased against darker skin tones. We propose to reduce this bias through multi-modal fusion with a complementary and fairer modality - radar. Through a novel debiasing oriented fusion framework, we achieve performance gains over all tested baselines and achieve skin tone fairness improvements over the RGB modality. That is, the associated Pareto frontier between performance and fairness is improved when compared to the RGB modality. In addition, performance improvements are obtained over the radar-based method, with small trade-offs in fairness. We also open-source the largest multi-modal remote heart-rate estimation dataset of paired camera and radar measurements with a focus on skin tone representation.

Rotation augmentations generally improve a model’s in-variance/equivariance to rotation - except in object detection. In object detection the shape is not known, therefore rotation creates a label ambiguity. We show that the de-facto method for bounding box label rotation, the Largest Box Method, creates very large labels, leading to poor performance and in many cases worse performance than using no rotation at all. We propose a new method of rotation augmentation that can be implemented in a few lines of code. First, we create a differentiable approximation of label accuracy and show that axis-aligning the bounding box around an ellipse is optimal. We then introduce Rotation Uncertainty (RU) Loss, allowing the model to adapt to the uncertainty of the labels. On five different datasets (including COCO, PascalVOC, and Transparent Object Bin Picking), this approach improves the rotational invariance of both one-stage and two-stage architectures when measured with AP, AP50, and AP75.

We present a novel time-resolved light transport decomposition method using thermal imaging. Because the speed of heat propagation is much slower than the speed of light propagation, the transient transport of far infrared light can be observed at a video frame rate. A key observation is that the thermal image looks similar to the visible light image in an appropriately controlled environment. This implies that conventional computer vision techniques can be straightforwardly applied to the thermal image. We show that the diffuse component in the thermal image can be separated, and therefore, the surface normals of objects can be estimated by the Lambertian photometric stereo. The effectiveness of our method is evaluated by conducting real-world experiments, and its applicability to black body, transparent, and translucent objects is shown.

Segmentation of transparent objects is a hard, open problem in computer vision. Transparent objects lack texture of their own, adopting instead the texture of scene background. This paper reframes the problem of transparent object segmentation into the realm of light polarization, i.e., the rotation of light waves. We use a polarization camera to capture multi-modal imagery and couple this with a unique deep learning backbone for processing polarization input data. Our method achieves instance segmentation on cluttered, transparent objects in various scene and background conditions, demonstrating an improvement over traditional image-based approaches. As an application we use this for robotic bin picking of transparent objects.

This paper presents a method of passive non-line-of-sight (NLOS) imaging using polarization cues. A key observation is that the oblique light has a different polarimetric signal. It turns out this effect is due to the polarization axis rotation, a phenomena which can be used to better condition the light transport matrix for non-line-of-sight imaging. Our analysis and results show that the use of a polarization for NLOS is both a standalone technique, as well as an enhancement technique to boost the results of other forms of passive NLOS imaging. We make a surprising finding that, despite 50% light attenuation from polarization optics, the gains from polarized NLOS are overall superior to unpolarized NLOS.

Optical 3D sensing technologies are exploited for many applications in autonomous vehicles, manufacturing, and consumer products. However, existing techniques may suffer in certain challenging conditions, where scattering may occur due to particles. While the light in the visible and near IR spectrum is affected by scattering, long-wave IR (LWIR) tends to experience less scattering, especially when the particles are much smaller than the incident radiation. We propose and demonstrate the expansion of structured light scanning approaches into the LWIR spectrum using a thermal camera and black body radiation source. We then validate the results produced against ground truth scans from traditional structured light scanners. Additional means for projecting these scanning patterns are also discussed alongside potential drawbacks and challenges of this technique associated with future adoption.

We propose a novel non-line-of-sight (NLOS) imaging framework with long-wave infrared (IR). At long-wave IR wavelengths, certain physical parameters are more favorable for high-fidelity reconstruction. In contrast to prior work in visible light NLOS, at long-wave IR wavelengths, the hidden heat source acts as a light source. This simplifies the problem to a single bounce problem. In addition, surface reflectance has a much stronger specular reflection in the long-wave IR spectrum than in the visible light spectrum. We reformulate a light transport model that leverages these favorable physical properties of long-wave IR. Specifically, we demonstrate 2D shape recovery and 3D localization of a hidden object. Furthermore, we demonstrate near real-time and robust NLOS pose estimation of a human figure, the first such demonstration, to our knowledge.

Dynamic interferometry enables snapshot recovery of phase images by using polarization phase shifting. However, the phase estimate is susceptible to influence from sources of ambient light having uncontrolled polarization. We present a novel method, dynamic heterodyne interferometry (DHI), as a means to mitigate phase bias from ambient light sources, while retaining dynamic potential.

A form of meter-scale, macroscopic interferometry is proposed using conventional time-of-flight (ToF) sensors. Today, ToF sensors use phase-based sampling, where the phase delay between emitted and received, high-frequency signals encodes distance. This paper examines an alternative ToF architecture, inspired by micron-scale, microscopic interferometry, that relies only on frequency sampling: we refer to our proposed macroscopic technique as Frequency-Domain Time of Flight (FD-ToF). The proposed architecture offers several benefits over existing phase ToF systems, such as robustness to phase wrapping and implicit resolution of multi-path interference, all while capturing the same number of subframes. A prototype camera is constructed to demonstrate macroscopic interferometry at meter scale.

We explore the question of whether phase-based time-of-flight (TOF) range cameras can be used for looking around corners and through scattering diffusers. By connecting TOF measurements with theory from array signal processing, we conclude that performance depends on two primary factors: camera modulation frequency and the width of the specular lobe (“shininess”) of the wall. For purely Lambertian walls, commodity TOF sensors achieve resolution on the order of meters between targets. For seemingly diffuse walls, such as posterboard, the resolution is drastically reduced, to the order of 10cm. In particular, we find that the relationship between reflectance and resolution is nonlinear—a slight amount of shininess can lead to a dramatic improvement in resolution. Since many realistic scenes exhibit a slight amount of shininess, we believe that off-the-shelf TOF cameras can look around corners.

Continuous-wave Time-of-flight (TOF) range imaging has become a commercially viable technology with many applications in computer vision and graphics. However, the depth images obtained from TOF cameras contain scene dependent errors due to multipath interference (MPI). Specifically, MPI occurs when multiple optical reflections return to a single spatial location on the imaging sensor. Many prior approaches to rectifying MPI rely on sparsity in optical reflections, which is an extreme simplification. In this paper, we correct MPI by combining the standard measurements from a TOF camera with information from direct and global light transport. We report results on both simulated experiments and physical experiments (using the Kinect sensor). Our results, evaluated against ground truth, demonstrate a quantitative improvement in depth accuracy.

Continuous improvement in optical sensing components, as well as recent advances in signal acquisition theory provide a great opportunity to reduce the cost and enhance the capabilities of depth sensing systems. In this paper we propose a new depth sensing architecture that exploits a fixed coded aperture to significantly reduce the number of sensors compared to conventional systems. We further develop a modeling and reconstruction framework, based on model-based compressed sensing, which characterizes a large variety of depth sensing systems. Our experiments demonstrate that it is possible to reduce the number of sensors by more than 85%, with negligible reduction on the sensing quality.

Coarse depth maps can be enhanced by using the shape information from polarization cues. We propose a framework to combine surface normals from polarization (hereafter polarization normals) with an aligned depth map. Polarization normals have not been used for depth enhancement before. This is because polarization normals suffer from physics-based artifacts, such as azimuthal ambiguity, refractive distortion and fronto-parallel signal degradation. We propose a framework to overcome these key challenges, allowing the benefits of polarization to be used to enhance depth maps. Our results demonstrate improvement with respect to state-of-the-art 3D reconstruction techniques.

In this paper, we consider the problem of Sparse Linear Operator identification which is also linked with the topic of Sparse Deconvolution. In its abstract form, the problem can be stated as follows: Given a well behaved probing function, is it possible to identify a Sparse Linear Operator from its response to the function? We present a constructive solution to this problem. Furthermore, our approach is devoid of any sparsity inducing penalty term and explores the idea of parametric modeling. Consequently, our algorithm is non-iterative by design and circumvents tuning of any regularization parameter. Our approach is computationally efficient when compared the ℓ0/ℓ1-norm regularized counterparts. Our work addresses a problem of industrial significance: decomposition of mixed-pixels in Time-of-Flight/Range imaging. In this case, each pixel records range measurements from multiple contributing depths and the goal is to isolate each depth. Practical experiments corroborate our theoretical set-up and establish the efficiency of our approach, that is, speed-up in processing with lesser mean squared error. We also derive Cramér-Rao Bounds for performance characterization.

Several computer vision algorithms require a sequence of photographs taken in different illumination conditions, which has spurred development in the area of illumination multiplexing. Various techniques for optimizing the multiplexing process already exist, but are geared toward regular or high speed cameras. Such cameras are fast, but code on the order of milliseconds. In this paper we propose a fusion of two popular contexts, time of flight range cameras and illumination multiplexing. Time of flight cameras are a low cost, consumer-oriented technology capable of acquiring range maps at 30 frames per second. Such cameras have a natural connection to conventional illumination multiplexing strategies as both paradigms rely on the capture of multiple shots and synchronized illumination. While previous work on illumination multiplexing has exploited coding at millisecond intervals, we repurpose sensors that are ordinarily used in time of flight imaging to demultiplex via nanosecond coding strategies.

Time of flight cameras produce real-time range maps at a relatively low cost using continuous wave amplitude modulation and demodulation. However, they are geared to measure range (or phase) for a single reflected bounce of light and suffer from systematic errors due to multipath interference. We re-purpose the conventional time of flight device for a new goal: to recover per-pixel sparse time profiles expressed as a sequence of impulses. With this modification, we show that we can not only address multipath interference but also enable new applications such as recovering depth of near-transparent surfaces, looking through diffusers and creating time-profile movies of sweeping light. Our key idea is to formulate the forward amplitude modulated light propagation as a convolution with custom codes, record samples by introducing a simple sequence of electronic time delays, and perform sparse deconvolution to recover sequences of Diracs that correspond to multipath returns. Applications to computer vision include ranging of near-transparent objects and subsurface imaging through diffusers. Our low cost prototype may lead to new insights regarding forward and inverse problems in light transport.