Karol Myszkowski

In human vision, the inputs perceived by each eye do not contribute equally to the final percept. Instead, visual dominance influences how these inputs are fused, giving more weight to one eye view over the other. While eye dominance has been traditionally treated as a static, eye-fixed property, recent evidence suggests that dominance can vary with viewing conditions. In this work, we systematically characterize dynamic visual dominance across the visual field, with a particular focus on peripheral vision, where perceptual asymmetries are most relevant for stereoscopic rendering. Through two complementary psychophysical experiments, we first show that tolerance to eye-asymmetric blur at the fovea under binocular viewing depends on gaze direction, confirming that eye dominance is not spatially invariant. We then show that peripheral dominance is primarily governed by retinal eccentricity, with consistent naso-temporal asymmetries and dominance reversals around the blind spots. We leverage our insights in a dominance-contingent rendering application, where additional blur is selectively applied to the perceptually non-dominant eye regions under binocular viewing. Compared to static dominance approaches, our method enables stronger localized quality reductions, illustrating the practical relevance of dynamic peripheral dominance for stereoscopic foveated rendering. Thus, our goal through this work is to show how visual dominance behaves dynamically in both the fovea and the periphery, indicating how foveation techniques could benefit from it.

Real-time path tracing increasingly operates under extremely low sampling budgets, often below one sample per pixel, as rendering complexity, resolution, and frame-rate requirements continue to rise. Superresolution is widely used in production because it reduces path-tracing cost by tracing rays on a coarser image grid and reconstructing missing details. This creates a uniform tradeoff between cost and spatial detail: every image region receives the same reduced ray budget, although path-tracing noise, reconstruction difficulty, and perceptual importance vary strongly across the image. Adaptive sampling offers a compelling alternative, but existing end-to-end approaches rely on approximations that break down in sparse regimes. We introduce an end-to-end adaptive sampling and denoising pipeline explicitly designed for the sub-1-spp regime. Our method uses a stochastic formulation of sample placement that enables gradient estimation despite discrete sampling decisions, allowing stable training of a neural sampler at low sampling budgets. To better align optimization with human perception, we propose a tone-mapping-aware training pipeline that integrates differentiable filmic operators and a state-of-the-art perceptual loss, preventing oversampling of regions with low visual impact. In addition, we introduce a gather-based pyramidal denoising filter and a learnable generalization of albedo demodulation tailored to sparse sampling. Our results show consistent improvements over uniform sparse sampling, with notably better reconstruction of perceptually critical details such as specular highlights and shadow boundaries, and demonstrate that adaptive sampling remains effective in the sub-1-spp regime.

Our ability to perceive and navigate the spatial world is a cornerstone of human experience, relying on the integration of visual and auditory cues to form a coherent sense of depth and distance. In stereoscopic 3D vision, depth perception requires fixation of both eyes on a target object, which is achieved through vergence movements, with convergence for near objects and divergence for distant ones. In contrast, auditory cues provide complementary depth information through variations in loudness, interaural differences (IAD), and the frequency spectrum. We investigate the interaction between visual and auditory cues and examine how contradictory auditory information can overdrive visual depth perception in virtual reality (VR). When a new visual target appears, we introduce a spatial discrepancy between the visual and auditory cues: the visual target is shifted closer to the previously fixated object, while the corresponding sound localization is displaced in the opposite direction. By integrating these conflicting cues through multimodal processing, the resulting percept is biased toward the intended depth location. This audiovisual fusion counteracts depth compression, thus reducing the required vergence magnitude and enabling faster gaze retargeting. Such audio-driven depth enhancement may further help mitigate the vergence-accommodation conflict (VAC) in scenarios where physical depth must be compressed. In a series of psychophysical studies, we first assess the efficiency of depth overdriving for various VR-relevant combinations of initial fixations and shifted target locations, considering different scenarios of audio displacements and their loudness and frequency parameters. Next, we quantify the resulting speedup in gaze retargeting for target shifts that can be successfully overdriven by sound manipulations. Finally, we apply our method in a naturalistic VR scenario where user interface interactions with the scene show an extended perceptual depth.

Real-time path tracing increasingly operates under extremely low sampling budgets, often below one sample per pixel, as rendering complexity, resolution, and frame-rate requirements continue to rise. While super-resolution is widely used in production, it uniformly sacrifices spatial detail and cannot exploit variations in noise, reconstruction difficulty, and perceptual importance across the image. Adaptive sampling offers a compelling alternative, but existing end-to-end approaches rely on approximations that break down in sparse regimes. We introduce an end-to-end adaptive sampling and denoising pipeline explicitly designed for the sub-1-spp regime. Our method uses a stochastic formulation of sample placement that enables gradient estimation despite discrete sampling decisions, allowing stable training of a neural sampler at low sampling budgets. To better align optimization with human perception, we propose a tonemapping-aware training pipeline that integrates differentiable filmic operators and a state-of-the-art perceptual loss, preventing oversampling of regions with low visual impact. In addition, we introduce a gather-based pyramidal denoising filter and a learnable generalization of albedo demodulation tailored to sparse sampling. Our results show consistent improvements over uniform sparse sampling, with notably better reconstruction of perceptually critical details such as specular highlights and shadow boundaries, and demonstrate that adaptive sampling remains effective even at minimal budgets.

We present MILO (Metric for Image- and Latent-space Optimization), a lightweight, multiscale, perceptual metric for full-reference image quality assessment (FR-IQA). MILO is trained using pseudo-MOS (Mean Opinion Score) supervision, in which reproducible distortions are applied to diverse images and scored via an ensemble of recent quality metrics that account for visual masking effects. This approach enables accurate learning without requiring large-scale human-labeled datasets. Despite its compact architecture, MILO outperforms existing metrics across standard FR-IQA benchmarks and offers fast inference suitable for real-time applications. Beyond quality prediction, we demonstrate the utility of MILO as a perceptual loss in both image and latent domains. In particular, we show that spatial masking modeled by MILO, when applied to latent representations from a VAE encoder within Stable Diffusion, enables efficient and perceptually aligned optimization. By combining spatial masking with a curriculum learning strategy, we first process perceptually less relevant regions before progressively shifting the optimization to more visually distorted areas. This strategy leads to significantly improved performance in tasks like denoising, super-resolution, and face restoration, while also reducing computational overhead. MILO thus functions as both a state-of-the-art image quality metric and as a practical tool for perceptual optimization in generative pipelines.

We present MILO (Metric for Image- and Latent-space Optimization), a lightweight, multiscale, perceptual metric for full-reference image quality assessment (FR-IQA). MILO is trained using pseudo-MOS (Mean Opinion Score) supervision, in which reproducible distortions are applied to diverse images and scored via an ensemble of recent quality metrics that account for visual masking effects. This approach enables accurate learning without requiring large-scale human-labeled datasets. Despite its compact architecture, MILO outperforms existing metrics across standard FR-IQA benchmarks and offers fast inference suitable for real-time applications. Beyond quality prediction, we demonstrate the utility of MILO as a perceptual loss in both image and latent domains. In particular, we show that spatial masking modeled by MILO, when applied to latent representations from a VAE encoder within Stable Diffusion, enables efficient and perceptually aligned optimization. By combining spatial masking with a curriculum learning strategy, we first process perceptually less relevant regions before progressively shifting the optimization to more visually distorted areas. This strategy leads to significantly improved performance in tasks like denoising, super-resolution, and face restoration, while also reducing computational overhead. MILO thus functions as both a state-of-the-art image quality metric and as a practical tool for perceptual optimization in generative pipelines.

We demonstrate generating HDR images using the concerted action of multiple black‐box, pre‐trained LDR image diffusion models. Common diffusion models are not HDR as, first, there is no sufficiently large HDR image dataset available to re‐train them, and, second, even if it was, re‐training such models is impossible for most compute budgets. Instead, we seek inspiration from the HDR image capture literature that traditionally fuses sets of LDR images, called “exposure brackets”, to produce a single HDR image. We operate multiple denoising processes to generate multiple LDR brackets that together form a valid HDR result. To this end, we introduce a brackets consistency term into the diffusion process to couple the brackets such that they agree across the exposure range they share. We demonstrate HDR versions of state‐of‐the‐art unconditional and conditional as well as restoration‐type (LDR2HDR) generative modeling.

The real world exhibits rich structure and detail across many scales of observation. It is difficult, however, to capture and represent a broad spectrum of scales using ordinary images. We devise a novel paradigm for learning a representation that captures an orders-of-magnitude variety of scales from an unstructured collection of ordinary images. We treat this collection as a distribution of scale-space slices to be learned using adversarial training, and additionally enforce coherency across slices. Our approach relies on a multiscale generator with carefully injected procedural frequency content, which allows to interactively explore the emerging continuous scale space. Training across vastly different scales poses challenges regarding stability, which we tackle using a supervision scheme that involves careful sampling of scales. We show that our generator can be used as a multiscale generative model, and for reconstructions of scale spaces from unstructured patches. Significantly outperforming the state of the art, we demonstrate zoom-in factors of up to 256x at high quality and scale consistency.

Human senses and perception are our mechanisms to explore the external world. In this context, visual saccades –rapid and coordinated eye movements– serve as a primary tool for awareness of our surroundings. Typically, our perception is not limited to visual stimuli alone but is enriched by cross-modal interactions, such as the combination of sight and hearing. In this work, we investigate the temporal and spatial relationship of these interactions, focusing on how auditory cues that precede visual stimuli influence saccadic latency –the time that it takes for the eyes to react and start moving towards a visual target. Our research, conducted within a virtual reality environment, reveals that auditory cues preceding visual information can significantly accelerate saccadic responses, but this effect plateaus beyond certain temporal thresholds. Additionally, while the spatial positioning of visual stimuli influences the speed of these eye movements, as reported in previous research, we find that the location of auditory cues with respect to their corresponding visual stimulus does not have a comparable effect. To validate our findings, we implement two practical applications: first, a basketball training task set in a more realistic environment with complex audiovisual signals, and second, an interactive farm game that explores previously untested values of our key factors. Lastly, we discuss various potential applications where our model could be beneficial.