Christopher Metzler

Jiayi Wu, Haoming Cai, Cornelia Fermuller et al.

While Video Diffusion Models (VDMs) excel at synthesizing high-fidelity videos, enabling precise camera and scene control remains challenging. Existing methods predominantly rely on implicit diffusion priors to generate unobserved regions, inevitably leading to structural collapse during high-dynamic movements or complex occlusions. To address this challenge, we propose Real2SAM2Real, a framework that leverages 3D lifting models (e.g., SAM3D) to extract an explicitly editable 3D cache, serving as a robust geometric scaffold for the VDM. By capturing the entire 3D volume of foreground entities rather than just their visible shells, this cache injects holistic spatial priors into the VDM, providing dependable 3D-aware guidance for complex scene dynamics. To effectively leverage this 3D guidance while preserving pre-trained priors, we design a Soft Spatial-Aligned Injection mechanism alongside a minimally invasive fine-tuning strategy tailored for VDMs. Furthermore, we employ masked normal maps as a cross-modal bridge to construct a 3D-free data curation and perturbation pipeline. Extensive experiments demonstrate that Real2SAM2Real enables precise, decoupled control over both camera trajectories and multi-entity motions. By utilizing the complementary context from generative 3D caches, our framework overcomes typical breakdowns caused by over-reliance on diffusion priors, maintaining exceptional spatiotemporal consistency under large camera shifts and severe occlusions. Crucially, by decoupling geometry from appearance, our VDM-tailored 3D cache eradicates perspective ambiguities caused by structural holes and erroneous facades, as well as misleading cues from reflections and refractions. Project website is available at https://jiayi-wu-leo.github.io/real2sam2real

Nishit Anand, Manan Suri, Christopher Metzler et al.

Controlling illumination in images is essential for photography and visual content creation. While closed-source models have demonstrated impressive illumination control, open-source alternatives either require heavy control inputs like depth maps or do not release their data and code. We present a fully open-source and reproducible pipeline for learning illumination control in diffusion models. Our approach builds a data engine that transforms well-lit images into supervised training triplets consisting of a poorly-illuminated input image, a natural language lighting instruction, and a well-illuminated output image. We finetune a diffusion model on this data and demonstrate significant improvements over baseline SD 1.5, SDXL, and FLUX.1-dev models in perceptual similarity, structural similarity, and identity preservation. Our work provides a reproducible solution built entirely with open-source tools and publicly available data. We release all our code, data, and model weights publicly.

Sachin Shah, Naitri Rajyaguru, Chahat Deep Singh et al.

Autonomous robots often rely on monocular cameras for odometry estimation and navigation. However, the scale ambiguity problem presents a critical barrier to effective monocular visual odometry. In this paper, we present CodedVO, a novel monocular visual odometry method that overcomes the scale ambiguity problem by employing custom optics to physically encode metric depth information into imagery. By incorporating this information into our odometry pipeline, we achieve state-of-the-art performance in monocular visual odometry with a known scale. We evaluate our method in diverse indoor environments and demonstrate its robustness and adaptability. We achieve a 0.08m average trajectory error in odometry evaluation on the ICL-NUIM indoor odometry dataset.

Hadi Alzayer, Kevin Zhang, Brandon Feng et al.

The reflective nature of the human eye is an underappreciated source of information about what the world around us looks like. By imaging the eyes of a moving person, we can collect multiple views of a scene outside the camera's direct line of sight through the reflections in the eyes. In this paper, we reconstruct a 3D scene beyond the camera's line of sight using portrait images containing eye reflections. This task is challenging due to 1) the difficulty of accurately estimating eye poses and 2) the entangled appearance of the eye iris and the scene reflections. Our method jointly refines the cornea poses, the radiance field depicting the scene, and the observer's eye iris texture. We further propose a simple regularization prior on the iris texture pattern to improve reconstruction quality. Through various experiments on synthetic and real-world captures featuring people with varied eye colors, we demonstrate the feasibility of our approach to recover 3D scenes using eye reflections.

Mingyang Xie, Matthew Chan, Christopher Metzler

High dynamic range (HDR) images are important for a range of tasks, from navigation to consumer photography. Accordingly, a host of specialized HDR sensors have been developed, the most successful of which are based on capturing variable per-pixel exposures. In essence, these methods capture an entire exposure bracket sequence at once in a single shot. This paper presents a straightforward but highly effective approach for turning an off-the-shelf polarization camera into a high-performance HDR camera. By placing a linear polarizer in front of the polarization camera, we are able to simultaneously capture four images with varied exposures, which are determined by the orientation of the polarizer. We develop an outlier-robust and self-calibrating algorithm to reconstruct an HDR image (at a single polarity) from these measurements. Finally, we demonstrate the efficacy of our approach with extensive real-world experiments.

Mingyang Xie, Numair Khan, Tianfu Wang et al.

Given a monocular video, the goal of video re-rendering is to generate views of the scene from a novel camera trajectory. Existing methods face two distinct challenges. Geometrically unconditioned models lack spatial awareness, leading to drift and deformation under viewpoint changes. On the other hand, geometrically-conditioned models depend on estimated depth and explicit reconstruction, making them susceptible to depth inaccuracies and calibration errors. We propose to address these challenges by using the implicit geometric knowledge embedded in the latent space of a large 4D reconstruction model to condition the video generation process. These latents capture scene structure in a continuous space without explicit reconstruction. Therefore, they provide a flexible representation that allows the pretrained diffusion prior to regularize errors more effectively. By jointly conditioning on these latents and source camera poses, we demonstrate that our model achieves state-of-the-art results on the video re-rendering task. Project webpage is https://lavr-4d-scene-rerender.github.io/

Kevin Zhang, Sakshum Kulshrestha, Christopher Metzler

Despite recent advances, developing general-purpose universal denoising and artifact-removal networks remains largely an open problem: Given fixed network weights, one inherently trades-off specialization at one task (e.g.,~removing Poisson noise) for performance at another (e.g.,~removing speckle noise). In addition, training such a network is challenging due to the curse of dimensionality: As one increases the dimensions of the specification-space (i.e.,~the number of parameters needed to describe the noise distribution) the number of unique specifications one needs to train for grows exponentially. Uniformly sampling this space will result in a network that does well at very challenging problem specifications but poorly at easy problem specifications, where even large errors will have a small effect on the overall mean squared error. In this work we propose training denoising networks using an adaptive-sampling/active-learning strategy. Our work improves upon a recently proposed universal denoiser training strategy by extending these results to higher dimensions and by incorporating a polynomial approximation of the true specification-loss landscape. This approximation allows us to reduce training times by almost two orders of magnitude. We test our method on simulated joint Poisson-Gaussian-Speckle noise and demonstrate that with our proposed training strategy, a single blind, generalist denoiser network can achieve peak signal-to-noise ratios within a uniform bound of specialized denoiser networks across a large range of operating conditions. We also capture a small dataset of images with varying amounts of joint Poisson-Gaussian-Speckle noise and demonstrate that a universal denoiser trained using our adaptive-sampling strategy outperforms uniformly trained baselines.

Ziyuan Qu, Omkar Vengurlekar, Mohamad Qadri et al.

Differentiable 3D-Gaussian splatting (GS) is emerging as a prominent technique in computer vision and graphics for reconstructing 3D scenes. GS represents a scene as a set of 3D Gaussians with varying opacities and employs a computationally efficient splatting operation along with analytical derivatives to compute the 3D Gaussian parameters given scene images captured from various viewpoints. Unfortunately, capturing surround view ($360^{\circ}$ viewpoint) images is impossible or impractical in many real-world imaging scenarios, including underwater imaging, rooms inside a building, and autonomous navigation. In these restricted baseline imaging scenarios, the GS algorithm suffers from a well-known 'missing cone' problem, which results in poor reconstruction along the depth axis. In this manuscript, we demonstrate that using transient data (from sonars) allows us to address the missing cone problem by sampling high-frequency data along the depth axis. We extend the Gaussian splatting algorithms for two commonly used sonars and propose fusion algorithms that simultaneously utilize RGB camera data and sonar data. Through simulations, emulations, and hardware experiments across various imaging scenarios, we show that the proposed fusion algorithms lead to significantly better novel view synthesis (5 dB improvement in PSNR) and 3D geometry reconstruction (60% lower Chamfer distance).

Jingxi Chen, Brandon Y. Feng, Haoming Cai et al.

This paper addresses the novel challenge of ``rewinding'' time from a single captured image to recover the fleeting moments missed just before the shutter button is pressed. This problem poses a significant challenge in computer vision and computational photography, as it requires predicting plausible pre-capture motion from a single static frame, an inherently ill-posed task due to the high degree of freedom in potential pixel movements. We overcome this challenge by leveraging the emerging technology of neuromorphic event cameras, which capture motion information with high temporal resolution, and integrating this data with advanced image-to-video diffusion models. Our proposed framework introduces an event motion adaptor conditioned on event camera data, guiding the diffusion model to generate videos that are visually coherent and physically grounded in the captured events. Through extensive experimentation, we demonstrate the capability of our approach to synthesize high-quality videos that effectively ``rewind'' time, showcasing the potential of combining event camera technology with generative models. Our work opens new avenues for research at the intersection of computer vision, computational photography, and generative modeling, offering a forward-thinking solution to capturing missed moments and enhancing future consumer cameras and smartphones. Please see the project page at https://timerewind.github.io/ for video results and code release.

Zijie Cai, Christopher Metzler

Monocular depth estimation has recently progressed beyond ordinal depth to provide metric depth predictions. However, its reliability in underwater environments remains limited due to light attenuation and scattering, color distortion, turbidity, and the lack of high-quality metric ground truth data. In this paper, we present a comprehensive benchmark of zero-shot and fine-tuned monocular metric depth estimation models on real-world underwater datasets with metric depth annotations, including FLSea and SQUID. We evaluated a diverse set of state-of-the-art Vision Foundation Models across a range of underwater conditions and depth ranges. Our results show that large-scale models trained on terrestrial data (real or synthetic) are effective in in-air settings, but perform poorly underwater due to significant domain shifts. To address this, we fine-tune Depth Anything V2 with a ViT-S backbone encoder on a synthetic underwater variant of the Hypersim dataset, which we simulated using a physically based underwater image formation model. Our fine-tuned model consistently improves performance across all benchmarks and outperforms baselines trained only on the clean in-air Hypersim dataset. This study presents a detailed evaluation and visualization of monocular metric depth estimation in underwater scenes, emphasizing the importance of domain adaptation and scale-aware supervision for achieving robust and generalizable metric depth predictions using foundation models in challenging environments.

Adam Yang, Nadula Kadawedduwa, Tianfu Wang et al.

Accurately reconstructing the 3D structure of tornadoes is critically important for understanding and preparing for this highly destructive weather phenomenon. While modern 3D scene reconstruction techniques, such as 3D Gaussian splatting (3DGS), could provide a valuable tool for reconstructing the 3D structure of tornados, at present we are critically lacking a controlled tornado dataset with which to develop and validate these tools. In this work we capture and release a novel multiview dataset of a small lab-based tornado. We demonstrate one can effectively reconstruct and visualize the 3D structure of this tornado using 3DGS.

Haoming Cai, Tsung-Wei Huang, Shiv Gehlot et al.

Text-to-image diffusion models excel at generating diverse portraits, but lack intuitive shadow control. Existing editing approaches, as post-processing, struggle to offer effective manipulation across diverse styles. Additionally, these methods either rely on expensive real-world light-stage data collection or require extensive computational resources for training. To address these limitations, we introduce Shadow Director, a method that extracts and manipulates hidden shadow attributes within well-trained diffusion models. Our approach uses a small estimation network that requires only a few thousand synthetic images and hours of training-no costly real-world light-stage data needed. Shadow Director enables parametric and intuitive control over shadow shape, placement, and intensity during portrait generation while preserving artistic integrity and identity across diverse styles. Despite training only on synthetic data built on real-world identities, it generalizes effectively to generated portraits with diverse styles, making it a more accessible and resource-friendly solution.

Sachin Shah, Matthew Albert Chan, Haoming Cai et al.

Point-spread-function (PSF) engineering is a well-established computational imaging technique that uses phase masks and other optical elements to embed extra information (e.g., depth) into the images captured by conventional CMOS image sensors. To date, however, PSF-engineering has not been applied to neuromorphic event cameras; a powerful new image sensing technology that responds to changes in the log-intensity of light. This paper establishes theoretical limits (Cramér Rao bounds) on 3D point localization and tracking with PSF-engineered event cameras. Using these bounds, we first demonstrate that existing Fisher phase masks are already near-optimal for localizing static flashing point sources (e.g., blinking fluorescent molecules). We then demonstrate that existing designs are sub-optimal for tracking moving point sources and proceed to use our theory to design optimal phase masks and binary amplitude masks for this task. To overcome the non-convexity of the design problem, we leverage novel implicit neural representation based parameterizations of the phase and amplitude masks. We demonstrate the efficacy of our designs through extensive simulations. We also validate our method with a simple prototype.

Haoming Cai, Jingxi Chen, Brandon Y. Feng et al.

tmospheric turbulence presents a significant challenge in long-range imaging. Current restoration algorithms often struggle with temporal inconsistency, as well as limited generalization ability across varying turbulence levels and scene content different than the training data. To tackle these issues, we introduce a self-supervised method, Consistent Video Restoration through Turbulence (ConVRT) a test-time optimization method featuring a neural video representation designed to enhance temporal consistency in restoration. A key innovation of ConVRT is the integration of a pretrained vision-language model (CLIP) for semantic-oriented supervision, which steers the restoration towards sharp, photorealistic images in the CLIP latent space. We further develop a principled selection strategy of text prompts, based on their statistical correlation with a perceptual metric. ConVRT's test-time optimization allows it to adapt to a wide range of real-world turbulence conditions, effectively leveraging the insights gained from pre-trained models on simulated data. ConVRT offers a comprehensive and effective solution for mitigating real-world turbulence in dynamic videos.