paper-with-me

Papers

CLIPDrawX: Primitive-based Explanations for Text Guided Sketch Synthesis

2023-12-04 · Nityanand Mathur, Shyam Marjit, Abhra Chaudhuri, Anjan Dutta

With the goal of understanding the visual concepts that CLIP associates with text prompts, we show that the latent space of CLIP can be visualized solely in terms of linear transformations on simple geometric primitives like circles and straight lines. Although existing approaches achieve this by sketch-synthesis-through-optimization, they do so on the space of B\'ezier curves, which exhibit a wastefully large set of structures that they can evolve into, as most of them are non-essential for generating meaningful sketches. We present CLIPDrawX, an algorithm that provides significantly better visualizations for CLIP text embeddings, using only simple primitive shapes like straight lines and circles. This constrains the set of possible outputs to linear transformations on these primitives, thereby exhibiting an inherently simpler mathematical form. The synthesis process of CLIPDrawX can be tracked end-to-end, with each visual concept being explained exclusively in terms of primitives. Implementation will be released upon acceptance. Project Page: $\href{https://clipdrawx.github.io/}{\text{https://clipdrawx.github.io/}}$.

📄 PDF Abstract BibTeX arXiv:2312.02345

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

SET Dynamic Sparse Training method where weight mask is updated randomly periodically
CLIP Contrastive Language-Image Pre-training (CLIP), consisting of a simplified version of ConVIRT trained from scratch, is an efficient method of image representation learning…

Similar Papers 제목 키워드 기반

Abstracting Sketches through Simple Primitives

2022-07-27 · Stephan Alaniz, Massimiliano Mancini, Anjan Dutta, Diego Marcos 외

Humans show high-level of abstraction capabilities in games that require quickly communicating object information. They decompose the message content into multiple parts and communicate them in an interpretable protocol.…

Image RetrievalRetrievalSketch-Based Image RetrievalSketch Recognition

SketchGen: Generating Constrained CAD Sketches

2021-06-04 · NeurIPS 2021 12 · Wamiq Reyaz Para, Shariq Farooq Bhat, Paul Guerrero, Tom Kelly 외

Computer-aided design (CAD) is the most widely used modeling approach for technical design. The typical starting point in these designs is 2D sketches which can later be extruded and combined to obtain complex three-dime…

CAD-Tokenizer: Towards Text-based CAD Prototyping via Modality-Specific Tokenization

2025-09-25 · Ruiyu Wang, Shizhao Sun, Weijian Ma, Jiang Bian arxiv

Computer-Aided Design (CAD) is a foundational component of industrial prototyping, where models are defined not by raw coordinates but by construction sequences such as sketches and extrusions. This sequential structure …

Instruction Following

Point2Primitive: CAD Reconstruction from Point Cloud by Direct Primitive Prediction

2025-05-04 · Cheng Wang, Xinzhu Ma, Bin Wang, Shixiang Tang 외

Recovering CAD models from point clouds, especially the sketch-extrusion process, can be seen as the process of rebuilding the topology and extrusion primitives. Previous methods utilize implicit fields for sketch repres…

CAD Reconstruction

Modular Multitask Reinforcement Learning with Policy Sketches

2016-11-06 · ICML 2017 8 · Jacob Andreas, Dan Klein, Sergey Levine

We describe a framework for multitask deep reinforcement learning guided by policy sketches. Sketches annotate tasks with sequences of named subtasks, providing information about high-level structural relationships among…

continuous-controlContinuous ControlDeep Reinforcement Learningreinforcement-learning+2