SketchImage → Imageacademic

LiteGE: Shape Descriptor Creation Process

Figure 1: Illustration of shape descriptor creation process in LiteGE. First, each input point cloud is aligned to a canonical upright orientation. Next, the shape is voxelized and the informative voxels near the shapes surface are selected. Finally, we compute the unsigned distance (UDF) from the informative voxels to the shape to construct the final shape descriptor. This is as shown on the rightmost figure where we depicted the cross-section slice of the UDF heatmap through the center of the shape.

Input image
Generated result

Paper context

Paper title: LiteGE: Lightweight Geodesic Embedding for Efficient Geodesics Computation and Non-Isometric Shape Correspondence Abstract: Computing geodesic distances on 3D surfaces is fundamental to many tasks in 3D vision and geometry processing, with deep connections to tasks such as shape correspondence. Recent learning-based methods achieve strong performance but rely on large 3D backbones, leading to high memory usage and latency, which limit their use in interactive or resource-constrained settings. We introduce LiteGE, a lightweight approach that constructs compact, category-aware shape descriptors by applying Principal Component Analysis (PCA) to unsigned distance field (UDFs) samples at informative voxels. This descriptor is efficient to compute and removes the need for high-capacity networks. LiteGE remains robust on sparse point clouds, supporting inputs with as few as 300 points, where prior methods fail. Extensive experiments show that LiteGE reduces memory usage and inference time by up to 300$\times$ compared to existing neural approaches. In addition, by exploiting the intrinsic relationship between geodesic distance and shape correspondence, LiteGE enables fast and accurate shape matching. Our method achieves up to 1000$\times$ speedup over state-of-the-art mesh-based approaches while maintaining comparable accuracy on non-isometric shape pairs, including evaluations on point-cloud inputs. Passages referencing this figure: Figure 1: Illustration of shape descriptor creation process in LiteGE. The overall pipeline is illustrated in Figure 1 . Each voxel is assigned a value of 1 if it lies within the shape and 0 otherwise (Figure 1 , middle).

The prompt

A reference image is attached above. It is my rough sketch of what I
want my final figure to look like — sometimes hand-drawn, sometimes
an AI quick-draft. The quality is rough; details may be wrong; some
elements may be missing — but it shows the STRUCTURE / SPATIAL LAYOUT
I'm going for.

I've also shared the paper title + abstract + method section + figure
caption + paragraphs that reference this figure.

TASK: Refine my rough sketch into a polished publication-quality figure.

  - Preserve the SPATIAL STRUCTURE of the sketch: where the boxes are,
    how they connect, the overall reading order, the rough proportions.
  - You may correct details: better text labels (use the paper context
    to get the right component names), cleaner shapes, real icons
    instead of stick-figure placeholders.
  - Do NOT regenerate from scratch with a different layout. The
    finished figure must be visibly the same composition as the sketch.

If your output bears no spatial resemblance to the reference sketch,
you've failed the task. Refine the sketch — don't replace it. Just
give me the polished figure.

Try this prompt now

Open it inside the generator with the prompt pre-filled.

Try this prompt

Related prompts