Can Hallucination Correction Improve Video-Language Alignment?

Large Vision-Language Models often generate hallucinated content that is not grounded in its visual inputs. While prior work focuses on mitigating hallucinations, we instead explore leveraging hallucination correction as a training objective to improve video-language alignment. We introduce HACA, a self-training framework learning to correct hallucinations in descriptions that do not align with the video content. By identifying and correcting inconsistencies, HACA enhances the model's ability to align video and textual representations for spatio-temporal reasoning. Our experimental results show consistent gains in video-caption binding and text-to-video retrieval tasks, demonstrating that hallucination correction-inspired tasks serve as an effective strategy for improving vision and language alignment.

Flash-Split: 2D Reflection Removal with Flash Cues and Latent Diffusion Separation

Transparent surfaces, such as glass, create complex reflections that obscure images and challenge downstream computer vision applications. We introduce Flash-Split, a robust framework for separating transmitted and reflected light using a single (potentially misaligned) pair of flash/no-flash images. Our core idea is to perform latent-space reflection separation while leveraging the flash cues. Specifically, Flash-Split consists of two stages. Stage 1 separates apart the reflection latent and transmission latent via a dual-branch diffusion model conditioned on an encoded flash/no-flash latent pair, effectively mitigating the flash/no-flash misalignment issue. Stage 2 restores high-resolution, faithful details to the separated latents, via a cross-latent decoding process conditioned on the original images before separation. By validating Flash-Split on challenging real-world scenes, we demonstrate state-of-the-art reflection separation performance and significantly outperform the baseline methods.

Flash-Splat: 3D Reflection Removal with Flash Cues and Gaussian Splats

We introduce a simple yet effective approach for separating transmitted and reflected light. Our key insight is that the powerful novel view synthesis capabilities provided by modern inverse rendering methods (e.g.,~3D Gaussian splatting) allow one to perform flash/no-flash reflection separation using unpaired measurements -- this relaxation dramatically simplifies image acquisition over conventional paired flash/no-flash reflection separation methods. Through extensive real-world experiments, we demonstrate our method, Flash-Splat, accurately reconstructs both transmitted and reflected scenes in 3D. Our method outperforms existing 3D reflection separation methods, which do not leverage illumination control, by a large margin. Our project webpage is at https://flash-splat.github.io/.

WaveMo: Learning Wavefront Modulations to See Through Scattering

Imaging through scattering media is a fundamental and pervasive challenge in fields ranging from medical diagnostics to astronomy. A promising strategy to overcome this challenge is wavefront modulation, which induces measurement diversity during image acquisition. Despite its importance, designing optimal wavefront modulations to image through scattering remains under-explored. This paper introduces a novel learning-based framework to address the gap. Our approach jointly optimizes wavefront modulations and a computationally lightweight feedforward "proxy" reconstruction network. This network is trained to recover scenes obscured by scattering, using measurements that are modified by these modulations. The learned modulations produced by our framework generalize effectively to unseen scattering scenarios and exhibit remarkable versatility. During deployment, the learned modulations can be decoupled from the proxy network to augment other more computationally expensive restoration algorithms. Through extensive experiments, we demonstrate our approach significantly advances the state of the art in imaging through scattering media. Our project webpage is at https://wavemo-2024.github.io/.

TimeRewind: Rewinding Time with Image-and-Events Video Diffusion

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.

ConVRT: Consistent Video Restoration Through Turbulence with Test-time Optimization of Neural Video Representations

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.

Snapshot High Dynamic Range Imaging with a Polarization Camera

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.

Roadmap on Deep Learning for Microscopy

Through digital imaging, microscopy has evolved from primarily being a means for visual observation of life at the micro- and nano-scale, to a quantitative tool with ever-increasing resolution and throughput. Artificial intelligence, deep neural networks, and machine learning are all niche terms describing computational methods that have gained a pivotal role in microscopy-based research over the past decade. This Roadmap is written collectively by prominent researchers and encompasses selected aspects of how machine learning is applied to microscopy image data, with the aim of gaining scientific knowledge by improved image quality, automated detection, segmentation, classification and tracking of objects, and efficient merging of information from multiple imaging modalities. We aim to give the reader an overview of the key developments and an understanding of possibilities and limitations of machine learning for microscopy. It will be of interest to a wide cross-disciplinary audience in the physical sciences and life sciences.

MetaDIP: Accelerating Deep Image Prior with Meta Learning

Deep image prior (DIP) is a recently proposed technique for solving imaging inverse problems by fitting the reconstructed images to the output of an untrained convolutional neural network. Unlike pretrained feedforward neural networks, the same DIP can generalize to arbitrary inverse problems, from denoising to phase retrieval, while offering competitive performance at each task. The central disadvantage of DIP is that, while feedforward neural networks can reconstruct an image in a single pass, DIP must gradually update its weights over hundreds to thousands of iterations, at a significant computational cost. In this work we use meta-learning to massively accelerate DIP-based reconstructions. By learning a proper initialization for the DIP weights, we demonstrate a 10x improvement in runtimes across a range of inverse imaging tasks. Moreover, we demonstrate that a network trained to quickly reconstruct faces also generalizes to reconstructing natural image patches.

TurbuGAN: An Adversarial Learning Approach to Spatially-Varying Multiframe Blind Deconvolution with Applications to Imaging Through Turbulence

We present a self-supervised and self-calibrating multi-shot approach to imaging through atmospheric turbulence, called TurbuGAN. Our approach requires no paired training data, adapts itself to the distribution of the turbulence, leverages domain-specific data priors, outperforms existing approaches, and can generalize from tens to tens of thousands of measurements. We achieve such functionality through an adversarial sensing framework adapted from CryoGAN, which uses a discriminator network to match the distributions of captured and simulated measurements. Our framework builds on CryoGAN by (1) generalizing the forward measurement model to incorporate physically accurate and computationally efficient models for light propagation through anisoplanatic turbulence, (2) enabling adaptation to slightly misspecified forward models, and (3) leveraging domain-specific prior knowledge using pretrained generative networks, when available. We validate TurbuGAN in simulation using realistic models for atmospheric turbulence-induced distortion.