相关论文: Linton Stereo Illusion: Response on Johnston (1991…
Hyperspectral image super-resolution has attained widespread prominence to enhance the spatial resolution of hyperspectral images. However, convolution-based methods have encountered challenges in harnessing the global spatial-spectral…
The remarkable progress in computer vision over the last few years is, by and large, attributed to deep learning, fueled by the availability of huge sets of labeled data, and paired with the explosive growth of the GPU paradigm. While…
Stereo matching is close to hitting a half-century of history, yet witnessed a rapid evolution in the last decade thanks to deep learning. While previous surveys in the late 2010s covered the first stage of this revolution, the last five…
Accurate volume estimation of objects from visual data is a long-standing challenge in computer vision with significant applications in robotics, logistics, and smart health. Existing methods often rely on complex 3D reconstruction…
Answering complex visual questions like `Which red furniture can be used for sitting?' requires multi-step reasoning, including object recognition, attribute filtering, and relational understanding. Recent work improves interpretability in…
The wide-field spectroscopic survey telescope (WST) is proposed to become the next large optical/near infrared facility for the European Southern Observatory (ESO) once the Extremely Large Telescope (ELT) has become operational. While the…
A large wide-field telescope and camera with optical throughput over 200 m^2 deg^2 -- a factor of 50 beyond what we currently have -- would enable the detection of faint moving or bursting optical objects: from Earth threatening asteroids…
The paper "Is Complexity an Illusion?" (Bennett, 2024) provides a formalism for complexity, learning, inference, and generalization, and introduces a formal definition for a "policy". This reply shows that correct policies do not exist for…
Hallucination has been a long-standing and inevitable problem that hinders the application of Large Vision-Language Models (LVLMs) in domains that require high reliability. Various methods focus on improvement depending on data annotations…
Due to the expansion of our Universe, the redshift of distant objects changes with time. Although the amplitude of this redshift drift is small, it will be measurable with a decade-long campaigns on the next generation of telescopes. Here…
Multimodal Large Language Models (MLLMs) have demonstrated remarkable capabilities in vision-language understanding tasks. While these models often produce linguistically coherent output, they often suffer from hallucinations, generating…
Dynamic spatial reasoning from monocular video is essential for bridging visual intelligence and the physical world, yet remains challenging for vision-language models (VLMs). Prior approaches either verbalize spatial-temporal reasoning…
So far life-long learning (LLL) has been studied in relatively small-scale and relatively artificial setups. Here, we introduce a new large-scale alternative. What makes the proposed setup more natural and closer to human-like visual…
Stereo vision is an effective technique for depth estimation with broad applicability in autonomous urban and highway driving. While various deep learning-based approaches have been developed for stereo, the input data from a binocular…
The pursuit of high perceptual quality in image restoration has driven the development of revolutionary generative models, capable of producing results often visually indistinguishable from real data. However, as their perceptual quality…
Deep neural networks (DNNs) have recently been achieving state-of-the-art performance on a variety of pattern-recognition tasks, most notably visual classification problems. Given that DNNs are now able to classify objects in images with…
Our brain recognizes only a tiny fraction of sensory input, due to an information processing bottleneck. This blinds us to most visual inputs. Since we are blind to this blindness, only a recent framework highlights this bottleneck by…
We describe the making of a two-mirrors stereoscope, identical to the first historical one, with the advantage of employing digital images on LCD monitors. We surprised the public with it, because they do not imagine being possible to watch…
This paper introduces Stereo Any Video, a powerful framework for video stereo matching. It can estimate spatially accurate and temporally consistent disparities without relying on auxiliary information such as camera poses or optical flow.…
Visual illusions allow researchers to devise and test new models of visual perception. Here we show that artificial neural networks trained for basic visual tasks in natural images are deceived by brightness and color illusions, having a…