Related papers: ShapeCodeBench: A Renewable Benchmark for Percepti…

We present a pixel recursive super resolution model that synthesizes realistic details into images while enhancing their resolution. A low resolution image may correspond to multiple plausible high resolution images, thus modeling the super…

The evaluation of code-generating Large Language Models (LLMs) is fundamentally constrained by two intertwined challenges: a reliance on static, easily contaminated problem sources and the use of superficial, low-rigor testing. This paper…

Current 3D reconstruction methods typically generate outputs in the form of voxels, point clouds, or meshes. However, each of these formats has inherent limitations, such as rough surfaces and distorted structures. Additionally, these data…

We propose T2I-ReasonBench, a benchmark evaluating reasoning capabilities of text-to-image (T2I) models. It consists of four dimensions: Idiom Interpretation, Textual Image Design, Entity-Reasoning and Scientific-Reasoning. We propose a…

Current 3D self-supervised learning methods of 3D scenes face a data desert issue, resulting from the time-consuming and expensive collecting process of 3D scene data. Conversely, 3D shape datasets are easier to collect. Despite this,…

Using synthesized images to boost the performance of perception models is a long-standing research challenge in computer vision. It becomes more eminent in visual-centric autonomous driving systems with multi-view cameras as some long-tail…

We frame the task of predicting a semantic labeling as a sparse reconstruction procedure that applies a target-specific learned transfer function to a generic deep sparse code representation of an image. This strategy partitions training…

Editing images using natural language instructions has become a natural and expressive way to modify visual content; yet, evaluating the performance of such models remains challenging. Existing evaluation approaches often rely on image-text…

Automated segmentation of the vertebral column in Computed Tomography (CT) scans is a prerequisite for pathological assessment and surgical planning. However, state-of-the-art methods, particularly those based on Transformers or large-scale…

The development of generalizable Novel View Synthesis (NVS) models is critically limited by the scarcity of large-scale training data featuring diverse and precise camera trajectories. While real-world captures are photorealistic, they are…

Recent progress in text-to-image (T2I) generation underscores the importance of reliable benchmarks in evaluating how accurately generated images reflect the semantics of their textual prompt. However, (1) existing benchmarks lack the…

While recent video world models can generate highly realistic videos, their ability to perform semantic reasoning and planning remains unclear and unquantified. We introduce Target-Bench, the first benchmark that enables comprehensive…

Semantic correspondence aims to identify semantically meaningful relationships between different images and is a fundamental challenge in computer vision. It forms the foundation for numerous tasks such as 3D reconstruction, object…

Robots operating in unstructured environments require a comprehensive understanding of their surroundings, necessitating geometric and semantic information from sensor data. Traditional RGB-D processing pipelines focus primarily on…

Text-to-image diffusion models have shown impressive capabilities in generating realistic visuals from natural-language prompts, yet they often struggle with accurately binding attributes to corresponding objects, especially in prompts…

Scene-level neural volumetric reconstruction from monocular videos remains challenging, especially under severe domain shifts. Although recent advances in vision foundation models (VFMs) provide transferable generalized priors learned from…

We introduce \emph{ReMatching}, a novel shape correspondence solution based on the functional maps framework. Our method, by exploiting a new and appropriate \emph{re}-meshing paradigm, can target shape-\emph{matching} tasks even on meshes…

Thanks to recent advancements in scalable deep architectures and large-scale pretraining, text-to-video generation has achieved unprecedented capabilities in producing high-fidelity, instruction-following content across a wide range of…

Scene understanding is an important capability for robots acting in unstructured environments. While most SLAM approaches provide a geometrical representation of the scene, a semantic map is necessary for more complex interactions with the…

The advent of powerful neural classifiers has increased interest in problems that require both learning and reasoning. These problems are critical for understanding important properties of models, such as trustworthiness, generalization,…