Related papers: Looking at words and points with attention: a benc…
Recent advances in Multimodal Large Language Models (MLLMs) and diffusion-based generative models have substantially improved prompt-driven image editing. However, scene text editing remains challenging, as it requires models to precisely…
Text-to-CAD generation aims to create parametric CAD models from natural language, enabling rapid prototyping and intuitive design workflows. However, existing benchmarks focus on basic primitives and simple sketch-extrude sequences,…
Automatically generating descriptive captions for images is a well-researched area in computer vision. However, existing evaluation approaches focus on measuring the similarity between two sentences disregarding fine-grained semantics of…
Large language models (LLMs) often produce unsupported or unverifiable content, known as "hallucinations." To mitigate this, retrieval-augmented LLMs incorporate citations, grounding the content in verifiable sources. Despite such…
In this paper, we investigate an open research task of generating controllable 3D textured shapes from the given textual descriptions. Previous works either require ground truth caption labeling or extensive optimization time. To resolve…
3D content creation plays a vital role in various applications, such as gaming, robotics simulation, and virtual reality. However, the process is labor-intensive and time-consuming, requiring skilled designers to invest considerable effort…
Recently, several data-sets associating data to text have been created to train data-to-text surface realisers. It is unclear however to what extent the surface realisation task exercised by these data-sets is linguistically challenging. Do…
Large text-to-video models hold immense potential for a wide range of downstream applications. However, they struggle to accurately depict dynamic object interactions, often resulting in unrealistic movements and frequent violations of…
As the usage of 3D models increases, so does the importance of developing accurate 3D shape retrieval algorithms. A common approach is to calculate a shape descriptor for each object, which can then be compared to determine two objects'…
Text-driven 3D editing seeks to modify 3D scenes according to textual descriptions, and most existing approaches tackle this by adapting pre-trained 2D image editors to multi-view inputs. However, without explicit control over multi-view…
We introduce a benchmark to directly evaluate the alignment between human observers and vision models on a 3D shape inference task. We leverage an experimental design from the cognitive sciences which requires zero-shot visual inferences…
The controllability of 3D object generation methods is achieved through input text. Existing text-to-3D object generation methods primarily focus on generating a single object based on a single object description. However, these methods…
Despite recent advances in text-conditioned 3D indoor scene generation, there remain gaps in the evaluation of these methods. Existing metrics often measure realism by comparing generated scenes to a set of ground-truth scenes, but they…
Evaluating text-to-vision content hinges on two crucial aspects: visual quality and alignment. While significant progress has been made in developing objective models to assess these dimensions, the performance of such models heavily relies…
We propose a new paradigm to automatically generate training data with accurate labels at scale using the text-to-image synthesis frameworks (e.g., DALL-E, Stable Diffusion, etc.). The proposed approach1 decouples training data generation…
This paper addresses the performance bottlenecks of existing text-driven image generation methods in terms of semantic alignment accuracy and structural consistency. A high-fidelity image generation method is proposed by integrating…
Due to their significance in human communication, the automatic generation of co-speech gestures in artificial embodied agents has received a lot of attention. Although modern deep learning approaches can generate realistic-looking…
Language model benchmarks are pervasive and computationally-efficient proxies for real-world performance. However, many recent works find that benchmarks often fail to predict real utility. Towards bridging this gap, we introduce benchmark…
Conversational systems have become increasingly popular as a way for humans to interact with computers. To be able to provide intelligent responses, conversational systems must correctly model the structure and semantics of a conversation.…
Traditional metrics like BLEU and BERTScore fail to capture semantic fidelity in generative text-to-text tasks. We adapt the Cross-Examination Framework (CEF) for a reference-free, multi-dimensional evaluation by treating the source and…