Related papers: Not all Views are Created Equal: Analyzing Viewpoi…

Vision-based 3D semantic occupancy prediction is a critical task in 3D vision that integrates volumetric 3D reconstruction with semantic understanding. Existing methods, however, often rely on modular pipelines. These modules are typically…

Shape is an important physical property of natural and manmade 3D objects that characterizes their external appearances. Understanding differences between shapes and modeling the variability within and across shape classes, hereinafter…

The ultimate goal of many image-based modeling systems is to render photo-realistic novel views of a scene without visible artifacts. Existing evaluation metrics and benchmarks focus mainly on the geometric accuracy of the reconstructed…

Visual Foundation Models (VFMs) are becoming ubiquitous in computer vision, powering systems for diverse tasks such as object detection, image classification, segmentation, pose estimation, and motion tracking. VFMs are capitalizing on…

We analyze the observability of motion estimates from the fusion of visual and inertial sensors. Because the model contains unknown parameters, such as sensor biases, the problem is usually cast as a mixed identification/filtering, and the…

We propose an action-conditioned dynamics model that predicts scene changes caused by object and agent interactions in a viewpoint-invariant 3D neural scene representation space, inferred from RGB-D videos. In this 3D feature space, objects…

A core capability for robot manipulation is reasoning over where and how to stably place objects in cluttered environments. Traditionally, robots have relied on object-specific, hand-crafted heuristics in order to perform such reasoning,…

Vision-based approaches have become the dominant paradigm for traversability estimation in unstructured outdoor environments, typically adapting vision foundation models (VFMs) via semantic segmentation supervision. However, this paradigm…

Vision-based robotic policies often struggle with even minor viewpoint changes, underscoring the need for view-invariant visual representations. This challenge becomes more pronounced in real-world settings, where viewpoint variability is…

We aim at finetuning a vision-language model without hurting its out-of-distribution (OOD) generalization. We address two types of OOD generalization, i.e., i) domain shift such as natural to sketch images, and ii) zero-shot capability to…

Zero-Shot Anomaly Detection (ZSAD) is an emerging AD paradigm. Unlike the traditional unsupervised AD setting that requires a large number of normal samples to train a model, ZSAD is more practical for handling data-restricted real-world…

Models for Visual Question Answering (VQA) are notorious for their tendency to rely on dataset biases, as the large and unbalanced diversity of questions and concepts involved and tends to prevent models from learning to reason, leading…

Finding matching keypoints between images is a core problem in 3D computer vision. However, modern matchers struggle with large in-plane rotations. A straightforward mitigation is to learn rotation invariance via data augmentation. However,…

Since its inception, Visual Question Answering (VQA) is notoriously known as a task, where models are prone to exploit biases in datasets to find shortcuts instead of performing high-level reasoning. Classical methods address this by…

In this position paper, we consider the state of computer vision research with respect to invariance to the horizontal orientation of an image -- what we term reflection invariance. We describe why we consider reflection invariance to be an…

We investigate the robustness of vision transformers (ViTs) through the lens of their special patch-based architectural structure, i.e., they process an image as a sequence of image patches. We find that ViTs are surprisingly insensitive to…

Causal representation learning has attracted significant research interest during the past few years, as a means for improving model generalization and robustness. Causal representations of interventional image pairs (also called…

Generating consistent multiple views for 3D reconstruction tasks is still a challenge to existing image-to-3D diffusion models. Generally, incorporating 3D representations into diffusion model decrease the model's speed as well as…

Estimating correspondences between deformed shape instances is a long-standing problem in computer graphics; numerous applications, from texture transfer to statistical modelling, rely on recovering an accurate correspondence map. Many…

Visual perception, the brain's construction of a stable world from sensory data, faces several long-standing, fundamental challenges. While often studied separately, these problems have resisted a single, unifying computational framework.…