Search for: All records

We present ShapeLib, the first method that uses the priors of Large Language Models (LLMs) to design libraries of programmatic 3D shape abstractions. Our system accepts two forms of user-provided design intent: high-level text descriptions of functions to include in the output library and a small seed set of exemplar shapes. We discover a library of abstractions that matches this design intent with a guided LLM workflow that first proposes different ways of applying and implementing functions, and then validates these functions are helpful in representing seed set shapes. To extend beyond the seed set, we develop library-specific recognition networks that map shapes (represented as primitives, voxels, or point clouds) to programs that use these newly discovered abstractions. Across multiple modeling domains (split by shape category), we find that LLMs, when thoughtfully combined with geometric reasoning, can be guided to author libraries of abstraction functions that generalize across shape distributions. Our framework takes a step towards realizing the long-standing shape analysis aspiration of discovering reusable, programmatic shape abstractions while exposing interpretable, semantically aligned interfaces. Our extensive evaluation demonstrates that ShapeLib provides distinct advantages over prior alternative abstraction discovery works in terms of generalization, usability, and maintaining plausibility under manipulation. Finally, we demonstrate that ShapeLib's abstraction functions unlock a number of downstream applications, combining LLM reasoning over shape programs with geometry processing tools to support shape editing and generation workflows. 

Abstract As generative AI becomes ubiquitous, writers must decide if, when, and how to incorporate generative AI into their writing process. Educators must sort through their role in preparing students to make these decisions in a quickly evolving technological landscape. We created an AI-enabled writing tool that provides scaffolded use of a large language model as part of a research study on integrating generative AI into an upper division STEM writing-intensive course. Drawing on decades of research on integrating digital tools into instruction and writing research, we discuss the framework that drove our initial design considerations and instructional resources. We then share our findings from a year of design-based implementation research during the 2023–2024 academic year. Our original instruction framework identified the need for students to understand, access, prompt, corroborate, and incorporate the generative AI use effectively. In this paper, we explain the need for students to think first, before using AI, move through good enough prompting to agentic iterative prompting, and reflect on their use at the end. We also provide emerging best practices for instructors, beginning with identifying learning objectives, determining the appropriate AI role, revising the content, reflecting on the revised curriculum, and reintroducing learning as needed. We end with an indication of our future directions. 

In professional design workflows, designers often begin by creating sketch drawings before converting them into CAD programs. However, prior work on automatically interpreting these sketches has been limited to simplified inputs and fails to account for construction lines that are ubiquitous in real‐world drawings. We present CADrawer, a system that translates 3D sketches into CAD programs using an autoregressive approach, leveraging construction lines as a rich source of information for recovering intermediate CAD operations. At each step, CADrawer predicts the next modeling operation and its parameters based on a graph‐based representation of the sketch, which explicitly encodes spatial and temporal relationships between strokes. To improve generation quality, the system maintains multiple candidate programs in parallel, and a learned value function evaluates these partial programs to guide the search toward the most promising candidates. CADrawer is designed as a complement to 3D sketching interfaces, building on existing methods that creates 3D sketches. We evaluate our method across several datasets, including those containing dense construction lines and cases without ground‐truth B‐rep shapes. 

Understanding bimanual human hand activities is a critical problem in AI and robotics. We cannot build large models of bimanual activities because existing datasets lack the scale, coverage of diverse hand activities, and detailed annotations. We introduce GigaHands, a massive annotated dataset capturing 34 hours of bimanual hand activities from 56 subjects and 417 objects, totaling 14k motion clips derived from 183 million frames paired with 84k text annotations. Our markerless capture setup and data acquisition protocol enable fully automatic 3D hand and object estimation while minimizing the effort required for text annotation. The scale and diversity of GigaHands enable broad applications, including text-driven action synthesis, hand motion captioning, and dynamic radiance field reconstruction. 

We design a system that learns how to edit visual programs. Our edit network consumes a complete input program and a visual target. From this input, we task our network with predicting a local edit operation that could be applied to the input program to improve its similarity to the target. In order to apply this scheme for domains that lack program annotations, we develop a self-supervised learning approach that integrates this edit network into a bootstrapped finetuning loop along with a network that predicts entire programs in one-shot. Our joint finetuning scheme, when coupled with an inference procedure that initializes a population from the one-shot model and evolves members of this population with the edit network, helps to infer more accurate visual programs. Over multiple domains, we experimentally compare our method against the alternative of using only the one-shot model, and find that even under equal search-time budgets, our editing-based paradigm provides significant advantages. 

The ability to edit 3D assets with natural language presents a compelling paradigm to aid in the democratization of 3D content creation. However, while natural language is often effective at communicating general intent, it is poorly suited for specifying exact manipulation. To address this gap, we introduce ParSEL, a system that enablescontrollableediting of high-quality 3D assets with natural language. Given a segmented 3D mesh and an editing request, ParSEL produces aparameterizedediting program. Adjusting these parameters allows users to explore shape variations with exact control over the magnitude of the edits. To infer editing programs which align with an input edit request, we leverage the abilities of large-language models (LLMs). However, we find that although LLMs excel at identifying the initial edit operations, they often fail to infer complete editing programs, resulting in outputs that violate shape semantics. To overcome this issue, we introduce Analytical Edit Propagation (AEP), an algorithm which extends a seed edit with additional operations until a complete editing program has been formed. Unlike prior methods, AEP searches for analytical editing operations compatible with a range of possible user edits through the integration of computer algebra systems for geometric analysis. Experimentally, we demonstrate ParSEL's effectiveness in enabling controllable editing of 3D objects through natural language requests over alternative system designs. 

People grasp flexible visual concepts from a few examples. We explore a neurosymbolic system that learns how to infer programs that capture visual concepts in a domain-general fashion. We introduce Template Programs: programmatic expressions from a domain-specific language that specify structural and parametric patterns common to an input concept. Our framework supports multiple concept-related tasks, including few-shot generation and co-segmentation through parsing. We develop a learning paradigm that allows us to train networks that infer Template Programs directly from visual datasets that contain concept groupings. We run experiments across multiple visual domains: 2D layouts, Omniglot characters, and 3D shapes. We find that our method outperforms task-specific alternatives, and performs competitively against domain-specific approaches for the limited domains where they exist.