Related papers: Paint Outside the Box: Synthesizing and Selecting …
Most classical planners use grounding as a preprocessing step, essentially reducing planning to propositional logic. However, grounding involves instantiating all action rules with concrete object combinations, and results in large…
Generalization beyond the training distribution is a core challenge in machine learning. The common practice of mixing and shuffling examples when training neural networks may not be optimal in this regard. We show that partitioning the…
Filtering - the task of estimating the conditional distribution for states of a dynamical system given partial and noisy observations - is important in many areas of science and engineering, including weather and climate prediction.…
Neural Radiance Fields (NeRF) have recently gained a surge of interest within the computer vision community for its power to synthesize photorealistic novel views of real-world scenes. One limitation of NeRF, however, is its requirement of…
Visual Grounding (VG) aims to locate the most relevant region in an image, based on a flexible natural language query but not a pre-defined label, thus it can be a more useful technique than object detection in practice. Most…
We propose a novel setting for learning, where the input domain is the image of a map defined on the product of two sets, one of which completely determines the labels. We derive a new risk bound for this setting that decomposes into a bias…
Domain randomization through synthesis is a powerful strategy to train networks that are unbiased with respect to the domain of the input images. Randomization allows networks to see a virtually infinite range of intensities and artifacts…
Compositing is one of the most important editing operations for images and videos. The process of improving the realism of composite results is often called harmonization. Previous approaches for harmonization mainly focus on images. In…
We present a method of improving visual place recognition and metric localisation under very strong appear- ance change. We learn an invertable generator that can trans- form the conditions of images, e.g. from day to night, summer to…
Current wisdom suggests more labeled image data is always better, and obtaining labels is the bottleneck. Yet curating a pool of sufficiently diverse and informative images is itself a challenge. In particular, training image curation is…
Visual grounding is a task to locate the target indicated by a natural language expression. Existing methods extend the generic object detection framework to this problem. They base the visual grounding on the features from pre-generated…
While convolutional neural networks are dominating the field of computer vision, one usually does not have access to the large amount of domain-relevant data needed for their training. It thus became common to use available synthetic…
Recent breakthroughs in video generation have demonstrated an emerging capability termed Chain-of-Frames (CoF) reasoning, where models resolve complex tasks through the generation of continuous frames. While these models show promise for…
The goal of image harmonization is adjusting the foreground appearance in a composite image to make the whole image harmonious. To construct paired training images, existing datasets adopt different ways to adjust the illumination…
Vision foundation models (VFMs) such as DINOv2 and CLIP have achieved impressive results on various downstream tasks, but their limited feature resolution hampers performance in applications requiring pixel-level understanding. Feature…
We introduce IntrinsiX, a novel method that generates high-quality intrinsic images from text description. In contrast to existing text-to-image models whose outputs contain baked-in scene lighting, our approach predicts physically-based…
Despite the growing prevalence of black-box pre-trained models (PTMs) such as prediction API services, there remains a significant challenge in directly applying general models to real-world scenarios due to the data distribution gap.…
We study image segmentation from an information-theoretic perspective, proposing a novel adversarial method that performs unsupervised segmentation by partitioning images into maximally independent sets. More specifically, we group image…
In image editing, the most common task is pasting objects from one image to the other and then eventually adjusting the manifestation of the foreground object with the background object. This task is called image compositing. But image…
We investigate the problem of automatically placing an object into a background image for image compositing. Given a background image and a segmented object, the goal is to train a model to predict plausible placements (location and scale)…