Related papers: Slow Perception: Let's Perceive Geometric Figures …

Perception research is increasingly modelled using streetscapes, yet many approaches still rely on pixel features or object co-occurrence statistics, overlooking the explicit relations that shape human perception. This study proposes a…

Cognitive science research treats visual perception, the ability to understand and make sense of a visual input, as one of the early developmental signs of intelligence. Its TVPS-4 framework categorizes and tests human perception into seven…

In this paper, we will study the following pattern recognition problem: Every pattern is a 3-dimensional graph, its surface can be split up into some regions, every region is composed of the pixels with the approximately same colour value…

Despite the importance of shape perception in human vision, early neural image classifiers relied less on shape information for object recognition than other (often spurious) features. While recent research suggests that current large…

In the presence of occlusions and measurement noise, geometrically accurate scene reconstructions -- which fit the sensor data -- can still be physically incorrect. For instance, when estimating the poses and shapes of objects in the scene…

To endow machines with the ability to perceive the real-world in a three dimensional representation as we do as humans is a fundamental and long-standing topic in Artificial Intelligence. Given different types of visual inputs such as…

Many surface cues support three-dimensional shape perception, but people can sometimes still see shape when these features are missing -- in extreme cases, even when an object is completely occluded, as when covered with a draped cloth. We…

Large vision language models (LVLM) are the leading A.I approach for achieving a general visual understanding of the world. Models such as GPT, Claude, Gemini, and LLama can use images to understand and analyze complex visual scenes. 3D…

Prototypical part learning is emerging as a promising approach for making semantic segmentation interpretable. The model selects real patches seen during training as prototypes and constructs the dense prediction map based on the similarity…

Sketching is used as a ubiquitous tool of expression by novices and experts alike. In this thesis I explore two methods that help a system provide a geometric machine-understanding of sketches, and in-turn help a user accomplish a…

Computational approach to imaging around the corner, or non-line-of-sight (NLOS) imaging, is becoming a reality thanks to major advances in imaging hardware and reconstruction algorithms. A recent development towards practical NLOS imaging,…

MLP-based architectures, which consist of a sequence of consecutive multi-layer perceptron blocks, have recently been found to reach comparable results to convolutional and transformer-based methods. However, most adopt spatial MLPs which…

Geometric understanding - including depth and height perception - is fundamental to intelligence and crucial for navigating our environment. Despite the impressive capabilities of large Vision Language Models (VLMs), it remains unclear how…

Despite significant advancements, large multimodal models (LMMs) still struggle to bridge the gap between low-level visual perception -- focusing on shapes, sizes, and layouts -- and high-level language reasoning, such as semantics and…

Large Vision Language Models (LVLMs) have achieved remarkable performance in various vision-language tasks. However, it is still unclear how accurately LVLMs can perceive visual information in images. In particular, the capability of LVLMs…

Reasoning-augmented vision language models (VLMs) generate explicit chains of thought that promise greater capability and transparency but also introduce new failure modes: models may reach correct answers via visually unfaithful…

Object detection and recognition are important problems in computer vision. Since these problems are meta-heuristic, despite a lot of research, practically usable, intelligent, real-time, and dynamic object detection/recognition methods are…

Despite remarkable progress in computer vision, modern recognition systems remain fundamentally limited by their dependence on rich, redundant visual inputs. In contrast, humans can effortlessly understand sparse, minimal representations…

We investigate the ability of Vision Language Models (VLMs) to perform visual perspective taking using a new set of visual tasks inspired by established human tests. Our approach leverages carefully controlled scenes in which a single…

Learning neural implicit fields of 3D shapes is a rapidly emerging field that enables shape representation at arbitrary resolutions. Due to the flexibility, neural implicit fields have succeeded in many research areas, including shape…